Machine Learning Predicts How Cancer Patients Will Respond to Therapy – HealthITAnalytics.com

November 18, 2020 -A machine learning algorithm accurately determined how well skin cancer patients would respond to tumor-suppressing drugs in four out of five cases, according to research conducted by a team from NYU Grossman School of Medicine and Perlmutter Cancer Center.

The study focused on metastatic melanoma, a disease that kills nearly 6,800 Americans each year. Immune checkpoint inhibitors, which keep tumors from shutting down the immune systems attack on them, have been shown to be more effective than traditional chemotherapies for many patients with melanoma.

However, half of patients dont respond to these immunotherapies, and these drugs are expensive and often cause side effects in patients.

While immune checkpoint inhibitors have profoundly changed the treatment landscape in melanoma, many tumors do not respond to treatment, and many patients experience treatment-related toxicity, said corresponding study authorIman Osman, medical oncologist in the Departments of Dermatology and Medicine (Oncology) at New York University (NYU) Grossman School of Medicine and director of the Interdisciplinary Melanoma Program at NYU Langones Perlmutter Cancer Center.

An unmet need is the ability to accurately predict which tumors will respond to which therapy. This would enable personalized treatment strategies that maximize the potential for clinical benefit and minimize exposure to unnecessary toxicity.

READ MORE: How Social Determinants Data Can Enhance Machine Learning Tools

Researchers set out to develop a machine learning model that could help predict a melanoma patients response to immune checkpoint inhibitors. The team collected 302 images of tumor tissue samples from 121 men and women treated for metastatic melanoma with immune checkpoint inhibitors at NYU Langone hospitals.

They then divided these slides into 1.2 million portions of pixels, the small bits of data that make up images. These were fed into the machine learning algorithm along with other factors, such as the severity of the disease, which kind of immunotherapy regimen was used, and whether a patient responded to the treatment.

The results showed that the machine learning model achieved an AUC of 0.8 in both the training and validation cohorts, and was able to predict which patients with a specific type of skin cancer would respond well to immunotherapies in four out of five cases.

Our findings reveal that artificial intelligence is a quick and easy method of predicting how well a melanoma patient will respond to immunotherapy, said study first author Paul Johannet, MD, a postdoctoral fellow at NYU Langone Health and its Perlmutter Cancer Center.

Researchers repeated this process with 40 slides from 30 similar patients at Vanderbilt University to determine whether the results would be similar at a different hospital system that used different equipment and sampling techniques.

READ MORE: Simple Machine Learning Method Predicts Cirrhosis Mortality Risk

A key advantage of our artificial intelligence program over other approaches such as genetic or blood analysis is that it does not require any special equipment, said study co-author Aristotelis Tsirigos, PhD, director of applied bioinformatics laboratories and clinical informatics at the Molecular Pathology Lab at NYU Langone.

The team noted that aside from the computer needed to run the program, all materials and information used in the Perlmutter technique are a standard part of cancer management that most, if not all, clinics use.

Even the smallest cancer center could potentially send the data off to a lab with this program for swift analysis, said Osman.

The machine learning method used in the study is also more streamlined than current predictive tools, such as analyzing stool samples or genetic information, which promises to reduce treatment costs and speed up patient wait times.

Several recent attempts to predict immunotherapy responses do so with robust accuracy but use technologies, such as RNA sequencing, that are not readily generalizable to the clinical setting, said corresponding study authorAristotelis Tsirigos, PhD, professor in the Institute for Computational Medicine at NYU Grossman School of Medicine and member of NYU Langones Perlmutter Cancer Center.

READ MORE: Machine Learning Forecasts Prognosis of COVID-19 Patients

Our approach shows that responses can be predicted using standard-of-care clinical information such as pre-treatment histology images and other clinical variables.

However, researchers also noted that the algorithm is not yet ready for clinical use until they can boost the accuracy from 80 percent to 90 percent and test the algorithm at more institutions. The research team plans to collect more data to improve the performance of the model.

Even at its current level of accuracy, the model could be used as a screening method to determine which patients across populations would benefit from more in-depth tests before treatment.

There is potential for using computer algorithms to analyze histology images and predict treatment response, but more work needs to be done using larger training and testing datasets, along with additional validation parameters, in order to determine whether an algorithm can be developed that achieves clinical-grade performance and is broadly generalizable, said Tsirigos.

There is data to suggest that thousands of images might be needed to train models that achieve clinical-grade performance.

Read more from the original source:
Machine Learning Predicts How Cancer Patients Will Respond to Therapy - HealthITAnalytics.com

This New Machine Learning Tool Might Stop Misinformation – Digital Information World

Misinformation has always been a problem, but the combination of widespread social media as well as a loose definition of what can be seen as factual truth in recent times has lead to a veritable explosion in misinformation over the course of the past few years. The problem is so dire that in a lot of cases websites are made specifically because of the fact that this is the sort of thing that could potentially end up allowing misinformation to spread more easily, and this is a problem that might just have been addressed by a new machine learning tool.

This machine learning tool was developed by researchers at UCL, Berkeley and Cornell will be able to detect domain registration data and use this to ascertain whether the URL is legitimate or if it has been made specifically to legitimize a certain piece of information that people might be trying to spread around. A couple of other factors also come into play here. For example, if the identity of the person that registered the domain is private, this might be a sign that the site is not legitimate. The timing of the domain registration matters to. If it was done around the time a major news event broke out, such as the recent US presidential election, this is also a negative sign.

With all of that having been said and out of the way, it is important to note that this new machine learning tool has a pretty impressive success rate of about 92%, which is the proportion of fake domains it was able to discover. Being able to tell whether or not a news source is legitimate or whether it is direct propaganda is useful because of the fact that it can help reduce the likelihood that people might just end up taking the misinformation seriously.

Read the original here:
This New Machine Learning Tool Might Stop Misinformation - Digital Information World

Fujitsu, AIST and RIKEN Achieve Unparalleled Speed on MLPerf HPC Machine Learning Processing Benchmark – HPCwire

TOKYO, Nov 19, 2020 Fujitsu, the National Institute of Advanced Industrial Science and Technology (AIST), and RIKEN today announced a performance milestone in supercomputing, achieving the highest performance and claiming the ranking positions on the MLPerf HPC benchmark. The MLPerf HPC benchmark measures large-scale machine learning processing on a level requiring supercomputers and the parties achieved these outcomes leveraging approximately half of the AI-Bridging Cloud Infrastructure (ABCI) supercomputer system, operated by AIST, and about 1/10 of the resources of the supercomputer Fugaku, which is currently under joint development by RIKEN and Fujitsu.

Utilizing about half the computing resources of its system, ABCI achieved processing speeds 20 times faster than other GPU-type systems. That is the highest performance among supercomputers based on GPUs, computing devices specialized in deep learning. Similarly, about 1/10 of Fugaku was utilized to set a record for CPU-type supercomputers consisting of general-purpose computing devices only, achieving a processing speed 14 times faster than that of other CPU-type systems.

The results were presented as MLPerf HPC v0.7 on November 18th (November 19th Japan Time) at the 2020 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC20) event, which is currently being held online.

Background

MLPerf HPC is a performance competition in two benchmark programs: CosmoFlow(2), which predicts cosmological parameters, and DeepCAM, which identifies abnormal weather phenomena. The ABCI ranked first in metrics of all registered systems in the CosmoFlow benchmark program, with about half of the whole ABCI system, and Fugaku ranked second with measurement of about 1/10 of the whole system. The ABCI system delivered 20 times the performance of the other GPU types, while Fugaku delivered 14 times the performance of the other CPU types. ABCI achieved first place amongst all registered systems in the DeepCAM benchmark program as well, also with about half of the system. In this way, ABCI and Fugaku overwhelmingly dominated the top positions, demonstrating the superior technological capabilities of Japanese supercomputers in the field of machine learning.

Fujitsu, AIST, RIKEN and Fujitsu Laboratories Limited will release the software stacks including the library and the AI framework which accelerate the large-scale machine learning process developed for this measurement to the public. This move will make it easier to use large-scale machine learning with supercomputers, while its use in analyzing simulation results is anticipated to contribute to the detection of abnormal weather phenomena and to new discoveries in astrophysics. As a core platform for building Society 5.0, it will also contribute to solve social and scientific issues, as it is expected to expand to applications such as the creation of general-purpose language models that require enormous computational performance.

About MLPerf HPC

MLPerf is a machine learning benchmark community established in May 2018 for the purpose of creating a performance list of systems running machine learning applications. MLPerf developed MLPerf HPC as a new machine learning benchmark to evaluate the performance of machine learning calculations using supercomputers. It is used for supercomputers around the world and is expected to become a new industry standard. MLPerf HPC v0.7 evaluated performance on two real applications, CosmoFlow and DeepCAM, to measure large-scale machine learning performance requiring the use of a supercomputer.

All measurement data are available on the following website: https://mlperf.org/

Comments from the Partners

Fujitsu, Executive Director, Naoki Shinjo: The successful construction and optimization of the software stack for large-scale deep learning processing, executed in close collaboration with AIST, RIKEN, and many other stakeholders made this achievement a reality, helping us to successfully claim the top position in the MLPerf HPC benchmark in an important milestone for the HPC community. I would like to express my heartfelt gratitude to all concerned for their great cooperation and support. We are confident that these results will pave the way for the use of supercomputers for increasingly large-scale machine learning processing tasks and contribute to many research and development projects in the future, and we are proud that Japans research and development capabilities will help lead global efforts in this field.

Hirotaka Ogawa, Principal Research Manager, Artificial Intelligence Research Center, AIST: ABCI was launched on August 1, 2018 as an open, advanced, and high-performance computing infrastructure for the development of artificial intelligence technologies in Japan. Since then, it has been used in industry-academia-government collaboration and by a diverse range of businesses, to accelerate R&D and verification of AI technologies that utilize high computing power, and to advance social utilization of AI technologies. The overwhelming results of MLPerf HPC, the benchmark for large-scale machine learning processing, showed the world the high level of technological capabilities of Japans industry-academia-government collaboration. AISTs Artificial Intelligence Research Center is promoting the construction of large-scale machine learning models with high versatility and the development of its application technologies, with the aim of realizing easily-constructable AI. We expect that the results of this time will be utilized in such technological development.

Satoshi Matsuoka, Director General, RIKEN Center for Computational Science: In this memorable first MLPerf HPC, Fugaku, Japans top CPU supercomputer, along with AISTs ABCI, Japans top GPU supercomputer, exhibited extraordinary performance and results, serving as a testament to Japans ability to compete at an exceptional level on the global stage in the area of AI research and development. I only regret that we couldnt achieve the overwhelming performance as we did for HPL-AI to be compliant with inaugural regulations for MLPerf HPC benchmark. In the future, as we continue to further improve the performance on Fugaku, we will make ongoing efforts to take advantage of Fugakus super large-scale environment in the area of high-performance deep learning in cooperation with various stakeholders.

About Fujitsu

Fujitsu is a leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 130,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 3.9 trillion yen (US$35 billion) for the fiscal year ended March 31, 2020. For more information, please see http://www.fujitsu.com.

About National Institute of Advanced Industrial Science & Technology (AIST)

AIST is the largest public research institute established in 1882 in Japan. The research fields of AIST covers all industrial sciences, e.g., electronics, material science, life science, metrology, etc. Our missions are bridging the gap between basic science and industrialization and solving social problems facing the world. we prepare several open innovation platforms to contribute to these missions, where researchers in companies, university professors, graduated students, as well as AIST researchers, get together to achieve our missions. The open innovation platform established recently is The Global Zero Emission Research Center which contributes to achieving a zero-emission society collaborating with foreign researches.https://www.aist.go.jp/index_en.html

About RIKEN Center for Computational Science

RIKEN is Japans largest comprehensive research institution renowned for high-quality research in a diverse range of scientific disciplines. Founded in 1917 as a private research foundation in Tokyo, RIKEN has grown rapidly in size and scope, today encompassing a network of world-class research centers and institutes across Japan including the RIKEN Center for Computational Science (R-CCS), the home of the supercomputer Fugaku. As the leadership center of high-performance computing, the R-CCS explores the Science of computing, by computing, and for computing. The outcomes of the exploration the technologies such as open source software are its core competence. The R-CCS strives to enhance the core competence and to promote the technologies throughout the world.

Source: Fujitsu

See more here:
Fujitsu, AIST and RIKEN Achieve Unparalleled Speed on MLPerf HPC Machine Learning Processing Benchmark - HPCwire

SVG Tech Insight: Increasing Value of Sports Content Machine Learning for Up-Conversion HD to UHD – Sports Video Group

This fall SVG will be presenting a series of White Papers covering the latest advancements and trends in sports-production technology. The full series of SVGs Tech Insight White Papers can be found in the SVG Fall SportsTech Journal HERE.

Following the height of the 2020 global pandemic, live sports are starting to re-emerge worldwide albeit predominantly behind closed doors. For the majority of sports fans, video is the only way they can watch and engage with their favorite teams or players. This means the quality of the viewing experience itself has become even more critical.

With UHD being adopted by both households and broadcasters around the world, there is a marked expectation around visual quality. To realize these expectations in the immediate term, it will be necessary for some years to up-convert from HD to UHD when creating 4K UHD sports channels and content.

This is not so different from the early days of HD, where SD sporting related content had to be up-converted to HD. In the intervening years, however, machine learning as a technology has progressed sufficiently to be a serious contender for performing better up-conversions than with more conventional techniques, specifically designed to work for TV content.

Ideally, we want to process HD content into UHD with a simple black box arrangement.

The problem with conventional up-conversion, though, is that it does not offer an improved resolution, so does not fully meet the expectations of the viewer at home watching on a UHD TV. The question, therefore, becomes: can we do better for the sports fan? If so, how?

UHD is a progressive scan format, with the native TV formats being 38402160, known as 2160p59.64 (usually abbreviated to 2160p60) or 2160p50. The corresponding HD formats, with the frame/field rates set by region, are either progressive 1280720 (720p60 or 720p50) or interlaced 19201080 (1080i30 or 1080i25).

Conversion from HD to UHD for progressive images at the same rate is fairly simple. It can be achieved using spatial processing only. Traditionally, this might typically use a bi-cubic interpolation filter, (a 2-dimensional interpolation commonly used for photographic image scaling.) This uses a grid of 44 source pixels and interpolates intermediate locations in the center of the grid. The conversion from 1280720 to 38402160 requires a 3x scaling factor in each dimension and is almost the ideal case for an upsampling filter.

These types of filters can only interpolate, resulting in an image that is a better result than nearest-neighbor or bi-linear interpolation, but does not have the appearance of being a higher resolution.

Machine Learning (ML) is a technique whereby a neural network learns patterns from a set of training data. Images are large, and it becomes unfeasible to create neural networks that process this data as a complete set. So, a different structure is used for image processing, known as Convolutional Neural Networks (CNNs). CNNs are structured to extract features from the images by successively processing subsets from the source image and then processes the features rather than the raw pixels.

Up-conversion process with neural network processing

The inbuilt non-linearity, in combination with feature-based processing, mean CNNs can invent data not in the original image. In the case of up-conversion, we are interested in the ability to create plausible new content that was not present in the original image, but that doesnt modify the nature of the image too much. The CNN used to create the UHD data from the HD source is known as the Generator CNN.

When input source data needs to be propagated through the whole chain, possibly with scaling involved, then a specific variant of a CNN known as a Residual Network (ResNet) is used. A ResNet has a number of stages, each of which includes a contribution from a bypass path that carries the input data. For this study, a ResNet with scaling stages towards the end of the chain was used as the Generator CNN.

For the Generator CNN to do its job, it must be trained with a set of known data patches of reference images and a comparison is made between the output and the original. For training, the originals are a set of high-resolution UHD images, down-sampled to produce HD source images, then up-converted and finally compared to the originals.

The difference between the original and synthesized UHD images is calculated by the compare function with the error signal fed back to the Generator CNN. Progressively, the Generator CNN learns to create an image with features more similar to original UHD images.

The training process is dependent on the data set used for training, and the neural network tries to fit the characteristics seen during training onto the current image. This is intriguingly illustrated in Googles AI Blog [1], where a neural network presented with a random noise pattern introduces shapes like the ones used during training. It is important that a diverse, representative content set is used for training. Patches from about 800 different images were used for training during the process of MediaKinds research.

The compare function affects the way the Generator CNN learns to process the HD source data. It is easy to calculate a sum of absolute differences between original and synthesized. This causes an issue due to training set imbalance; in this case, the imbalance is that real pictures have large proportions with relatively little fine detail, so the data set is biased towards regenerating a result like that which is very similar to the use of a bicubic interpolation filter.

This doesnt really achieve the objective of creating plausible fine detail.

Generative Adversarial Neural Networks (GANs) are a relatively new concept [2], where a second neural network, known as the Discriminator CNN, is used and is itself trained during the training process of the Generator CNN. The Discriminator CNN learns to detect the difference between features that are characteristic of original UHD images and synthesized UHD images. During training, the Discriminator CNN sees either an original UHD image or a synthesized UHD image, with the detection correctness fed back to the discriminator and, if the image was a synthesized one, also fed back to the Generator CNN.

Each CNN is attempting to beat the other: the Generator by creating images that have characteristics more like originals, while the Discriminator becomes better at detecting synthesized images.

The result is the synthesis of feature details that are characteristic of original UHD images.

With a GAN approach, there is no real constraint to the ability of the Generator CNN to create new detail everywhere. This means the Generator CNN can create images that diverge from the original image in more general ways. A combination of both compare functions can offer a better balance, retaining the detail regeneration, but also limiting divergence. This produces results that are subjectively better than conventional up-conversion.

Conversion from 1080i60 to 2160p60 is necessarily more complex than from 720p60. Starting from 1080i, there are three basic approaches to up-conversion:

Training data is required here, which must come from 2160p video sequences. This enables a set of fields to be created, which are then downsampled, with each field coming from one frame in the original 2160p sequence, so the fields are not temporally co-located.

Surprisingly, results from field-based up-conversion tended to be better than using de-interlaced frame conversion, despite using sophisticated motion-compensated de-interlacing: the frame-based conversion being dominated by the artifacts from the de-interlacing process. However, it is clear that potentially useful data from the opposite fields did not contribute to the result, and the field-based approach missed data that could produce a better result.

A solution to this is to use multiple fields data as the source data directly into a modified Generator CNN, letting the GAN learn how best to perform the deinterlacing function. This approach was adopted and re-trained with a new set of video-based data, where adjacent fields were also provided.

This led to both high visual spatial resolution and good temporal stability. These are, of course, best viewed as a video sequence, however an example of one frame from a test sequence shows the comparison:

Comparison of a sample frame from different up-conversion techniques against original UHD

Up-conversion using a hybrid GAN with multiple fields was effective across a range of content, but is especially relevant for the visual sports experience to the consumer. This offers a realistic means by which content that has more of the appearance of UHD can be created from both progressive and interlaced HD source, which in turn can enable an improved experience for the fan at home when watching a sports UHD channel.

1 A. Mordvintsev, C. Olah and M. Tyka, Inceptionism: Going Deeper into Neural Networks, 2015. [Online]. Available: https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html

2 I. e. a. Goodfellow, Generative Adversarial Nets, Neural Information Processing Systems Proceedings, vol. 27, 2014.

Read more here:
SVG Tech Insight: Increasing Value of Sports Content Machine Learning for Up-Conversion HD to UHD - Sports Video Group

How to recover data from a Mac with T2 or FileVault encryption and without a password – Macworld

Its hard thing to discover that a loved one is incapacitated or passed away, and the Mac or Macs they left behind cant be unlocked to retrieve photos, important financial or legal information, or any of their digital traces. If the main account or any administrative user password is unavailable, a newer Mac may be completely unrecoverable.

Many times, a person who experiences dementia may have already appointed or had appointed someone with the legal right to access their devices; someone who may know they were facing death or who had planned ahead with a will may have left their gear explicitly to someone, or appointed an executor who has rights. (This is not legal advice, by the way; consult an attorney with any questions about the legality of accessing such hardware.)

But the right or need to access a Mac doesnt mean one has the ability, and Apple has designed its systems to prevent its own ability to break through strong protections.

The T2 Security Chip found in newer Macs (see the list of Mac models here) brought iPhone- and iPad-style security and encryption to macOS, including Touch ID on laptops. The Macs startup volume is automatically encrypted at rest, separate from the long-running FileVault technology in macOS. (See How FileVault and the T2 Security Chip work together in newer Macs for more details.)

The T2 chip on a Mac automatically encrypts the startup drive as a way to improve security dramaticallyincluding rendering a drives contents unreadable if a device were lost or stolen. Without a fingerprint on a Touch ID-equipped Mac (for a computer thats running, logged in, and in the right circumstances) or a password for any Mac, even without FileVault enabled, the contents of the Macs drive could be permanently unavailable.

If the Mac in question is one of the above models, skip to Strategies to work around not having the password, later in this article.

If it doesnt have a T2 chip, you can try the following; if not, read on for what wont work, and then strategies to try without the password.

You may be able to mount a Mac as a volume on another Mac without a password using Target Disk Modeas long as FileVault wasnt enabled. You may not know if was, so you can try the following if both Macs have a FireWire (older models) or Thunderbolt 2 or 3 port:

Connect the computers.

Restart or startup the Mac you want to mount on the other while holding down the T key.

If it works, a volume icon appears on the other Mac.

If you receive a prompt to enter a password, then either FileVault is enabled or theres a T2 chip on the computeror even both.

However, if you dont have another Mac to try this with or they dont have compatible ports, you can also set up an external, bootable macOS drive with a version of macOS new enough to start up the computer in question and not too new for an older Mac. (Consult the Macs model to check on which system releases work with it.)

Heres how to boot from an external drive:

With a macOS startup volume installed on an external drive, plug it into the Mac you want to start up.

Either restart the Mac or start it up, holding down the Option key as it powers up.

A roughly formatted display showing available startup drives should appear. Click or use a keyboard to select and boot from that drive.

The internal drive shows up as a volume after macOS starts up.

If you cant start up from an external drive because youre prompted for a password or blocked in another fashion, or macOS prompts you for a password to mount the internal drive (as above), youre stuck.

In nearly every scenario involving either a Mac with a T2 chip, FileVault enabled, or both, you have to have an administrative accounts password, often the main or only account on a Mac:

With FileVault turned on with any Mac, a password has to be entered at startup to even start macOS running. Otherwise its startup volume remains unavailable.

With the T2 chip and no FileVault, a Mac will boot to the startup screen, but unless you had the password, even though the drives contents are available to a user, youd have to break into macOS to gain access to files. Because the T2 chip restricts starting up with an external drive without making a specific administrative change that requires a password, you wont even be able to boot off an external driveand youd need an account password after that to mount the drive when started up externally, in any case.

You might consider removing the hard drive as one strategy. But Macs of the last few years have drives that cant easily be removed or are impossible to remove at all. Even if you could mount a drive on another device, if FileVault is enabled or its a mac with a T2 chip, its impossible to decrypt the drives contents.

The Startup Security Manger on T2-equipped Macs prevents staring up from an external drive without changing settingswhich requires a password.

Dont give up yet, however.

Several strategies can help, some of them absurdly low tech:

Check for sticky notes, password books, or other places someone may have written down their password. This is surprisingly common, yet often overlooked. (The best hackers in movies always make a joke about it when asked what sophisticated cracking tool they will use: they just find the sticky note.)

Did the person ever give you a password as a backup in case they lost or forgot theirs? Check your messages, password manager, or notes.

Look for local backups. While startup drives may be encrypted via FileVault or the T2 chip, Time Machine and other backups typically arent, unless someone takes an extra step to encrypt the volume. (If they did that, they might also have taken steps to allow someone else to gain access later if they couldnt.) Look for a drive directly connected to the computer, to another computer on the network, or a Time Capsule, Apples discontinued networked Time Machine backup option.

Look for online backups. A person may be using a cloud-based backup storage system, like Backblaze or Carbonite, and you may be able to find the password for that if you cant find their Mac accounts password. Check credit-card bills to see if theyre using such a service.

Check iCloud. Again, you might be able to find or figure out their iCloud login, and retrieve photos and synced files from iCloud.

Look for other sync services. Dropbox, Google Drive, OneDrive, and other options can sync the contents of folders or nearly an entire drive from a computer to cloud-based storage.

Preparation always helps, too. If youre reading this column prospectivelybefore a problem has cropped upsee How to prepare your digital assets in case of death for advice on setting up yourself or helping someone else be set up for access when they cant provide a password.

This Mac 911 article is in response to a question submitted by Macworld reader Janvier.

Weve compiled a list of the questions we get asked most frequently along with answers and links to columns: read our super FAQ to see if your question is covered. If not, were always looking for new problems to solve! Email yours to mac911@macworld.com including screen captures as appropriate, and whether you want your full name used. Not every question will be answered, we dont reply to email, and we cannot provide direct troubleshooting advice.

Read the original:
How to recover data from a Mac with T2 or FileVault encryption and without a password - Macworld

Encryption Software Market 2020-2027 Growth Analysis, Key Insights and Future Development By Check Point Software Technologie, InterCrypto, Hewlett…

The Global Encryption Software Market report is designed to effectively guide as a singular point of reference to address all reader queries and manufacturer doubts that enable high revenue generation amidst neck-deep competition in the Encryption Software market. The report is also a unique guiding aid to encourage best industry practices and equivalent business decisions that leverage million-dollar growth opportunities.

According to research inputs, this global Encryption Software market is also likely to register a thumping growth of USD xx million in 2020 and is further anticipated to reach over xx million USD by the end of 2027, clocking at a steady CAGR of xx% through the forecast span, 2020-27.

Request a sample of Encryption Software Market report @ https://www.orbismarketreports.com/sample-request/145544?utm_source=Maia

Research analysts and industry experts through this report are also aiming to lend ample light on further essential determinants such as a meticulous review and analytical take of opportunity assessment, also encompassing threat and challenge analysis that constantly deter upward growth spurt in Encryption Software market.

Key Plyares Analyis: Global Encryption Software Market

Check Point Software TechnologieInterCryptoHewlett PackardEast-TecTrend MicroSymantecEntrustBloombaseCiscoIBM

COVID-19 Impact Analysis:

To enable mindful business discretion amidst catastrophic developments such as COVID-19 and its subsequent implications, this ready-to-refer research report on the global Encryption Software market is designed to answer the queries pertaining to the pandemic to emerge from catastrophic implications.

Thus, this thorough, meticulously crafted research report is in place to aid vital market specific decisions amongst relevant stakeholders who remain key influencers in directing favorable growth trajectory in the Encryption Software market.

Further in the course of the report, research experts and industry experts also unfurl considerable understanding on other important implication rendering features such as current, historical, as well as future prospects of the market that have substantial bearing on the growth spurt of the Encryption Software market.

This intensively compiled research report presentation is a versatile hub of innate knowledge factors such as sales volume and bulk production, pricing matrix and sales figures, overall growth review and margin, chances of growth in the future and their range amongst other additional growth determinants that influence growth in the Encryption Software market.

Browse the complete report @ https://www.orbismarketreports.com/global-encryption-software-market-size-share-growth-analysis-and-forecast-outlook-by-2027?utm_source=Maia

Understanding Regional Segmentation:

Further in its succeeding sectors of the report, this detailed presentation of the Encryption Software market offers vigorous details on regional belts and expansion projects identifying potential growth possibilities.

Furthermore, the report helps as a expedient guide to design and instrument probable growth routing activities across select regional hubs in the Encryption Software market. Frontline companies and their result-based growth approaches are also recruited in the report to emulate growth.

Encryption Software Market Analysis by Types:

Symmetric EncryptionAsymmetric EncryptionHashing

Encryption Software Market Analysis by Applications:

Whole DiskSingle-user File/folder LevelMulti-user File/folder LevelDatabaseApplication LevelEmail MessagesNetwork Traffic

The Report in a Nutshell:

1. A holistic documentation of current Encryption Software market influencers such as COVID-19 pandemic and consequent implications.

2. A rigorous real-time analytical review of the industrial developments, across a multi-faceted perspective to encourage lucrative business discretion.

3. A point-by-point overview of all major segments as well as cross sectional analysis of the aforementioned Encryption Software market, inclusive also of core manufacturer activity.

4. A thorough evaluation of regional developments, encapsulating diverse developments from a country-wise perspective.

5. A systematic representation of major opportunity mapping, competition intensity as well as barrier analysis to encourage wise business ventures.

Make an enquiry of this report @ https://www.orbismarketreports.com/enquiry-before-buying/145544?utm_source=Maia

ABOUT US:

With unfailing market gauging skills, Orbis Market Reports has been excelling in curating tailored business intelligence data across industry verticals. Constantly thriving to expand our skill development, our strength lies in dedicated intellectuals with dynamic problem solving intent, ever willing to mold boundaries to scale heights in market interpretation. We are equally backed by an elongated list of success stories and case studies that vouch for our extraordinary market research skills and milestones. Orbis Market Reports is a one-stop-solution to all market queries.

CONTACT US:

Address :- 6200 Savoy Drive,Suite 630 Houston, TX 77036Phone :- +1 210-667-2421Mail us: [emailprotected]

Read more from the original source:
Encryption Software Market 2020-2027 Growth Analysis, Key Insights and Future Development By Check Point Software Technologie, InterCrypto, Hewlett...

Is Now the Time to Start Protecting Government Data from Quantum Hacking? – Nextgov

My previous column about the possibility of pairing artificial intelligence with quantum computing to supercharge both technologies generated a storm of feedback via Twitter and email. Quantum computing is a science that is still somewhat misunderstood, even by scientists working on it, but might one day be extremely powerful. And artificial intelligence has some scary undertones with quite a few trust issues. So I understand the reluctance that people have when considering this marriage of technologies.

Unfortunately, we dont really get a say in this. The avalanche has already started, so its too late for all of us pebbles to vote against it. All we can do now is deal with the practical ramifications of these recent developments. The most critical right now is protecting government encryption from the possibility of quantum hacking.

Two years ago I warned that government data would soon be vulnerable to quantum hacking, whereby a quantum machine could easily shred the current AES encryption used to protect our most sensitive information. Government agencies like NIST have been working for years on developing quantum-resistant encryption schemes. But adding AI to a quantum computer might be the tipping point needed to give quantum the edge, while most of the quantum-resistant encryption protections are still being slowly developed. At least, that is what I thought.

One of the people who contacted me after my last article was Andrew Cheung, the CEO of 01 Communique Laboratory and IronCAP. They have a product available right now which can add quantum-resistant encryption to any email. Called IronCAP X, its available for free for individual users, so anyone can start protecting their email from the threat of quantum hacking right away. In addition to downloading the program to test, I spent about an hour interviewing Cheung about how quantum-resistant encryption works, and how agencies can keep their data protection one step ahead of some of the very same quantum computers they are helping to develop.

For Cheung, the road to quantum-resistant encryption began over 10 years ago, long before anyone was seriously engineering a quantum computer. It almost felt like we were developing a bulletproof vest before anyone had created a gun, Cheung said.

But the science of quantum-resistant encryption has actually been around for over 40 years, Cheung said. It was just never specifically called that. People would ask how we could develop encryption that would survive hacking by a really fast computer, he said. At first, nobody said the word quantum, but that is what we were ultimately working against.

According to Cheung, the key to creating quantum-resistant encryption is to get away from the core strength of computers in general, which is mathematics. He explained that RSA encryption used by the government today is fundamentally based on prime number factorization, where if you multiply two prime numbers together, the result is a number that can only be broken down into those primes. Breaking encryption involves trying to find those primes by trial and error.

So if you have a number like 21, then almost anyone can use factorization to quickly break it down and find its prime numbers, which are three and seven. If you have a number like 221, then it takes a little bit longer for a human to come up with 13 and 17 as its primes, though a computer can still do that almost instantaneously. But if you have something like a 500 digit number, then it would take a supercomputer more than a century to find its primes and break the related encryption. The fear is that quantum computers, because of the strange way they operate, could one day do that a lot more quickly.

To make it more difficult for quantum machines, or any other kind of fast computer, Cheung and his company developed an encryption method based on binary Goppa code. The code was named for the renowned Russian mathematician who invented it, Valerii Denisovich Goppa, and was originally intended to be used as an error-correcting code to improve the reliability of information being transmitted over noisy channels. The IronCAP program intentionally introduces errors into the information its protecting, and then authorized users can employ a special algorithm to decrypt it, but only if they have the private key so that the numerous errors can be removed and corrected.

What makes encryption based on binary Goppa code so powerful against quantum hacking is that you cant use math to guess at where or how the errors have been induced into the protected information. Unlike encryption based on prime number factorization, there isnt a discernible pattern, and theres no way to brute force guess at how to remove the errors. According to Cheung, a quantum machine, or any other fast system like a traditional supercomputer, cant be programmed to break the encryption because there is no system for it to use to begin its guesswork.

A negative aspect to binary Goppa code encryption, and also one of the reasons why Cheung says the protection method is not more popular today, is the size of the encryption key. Whether you are encrypting a single character or a terabyte of information, the key size is going to be about 250 kilobytes, which is huge compared with the typical 4 kilobyte key size for AES encryption. Even ten years ago, that might have posed a problem for many computers and communication methods, though it seems tiny compared with file sizes today. Still, its one of the main reasons why AES won out as the standard encryption format, Cheung says.

I downloaded the free IronCAP X application and easily integrated it into Microsoft Outlook. Using the application was extremely easy, and the encryption process itself when employing it to protect an email is almost instantaneous, even utilizing the limited power of an average desktop. And while I dont have access to a quantum computer to test its resilience against quantum hacking, I did try to extract the information using traditional methods. I can confirm that the data is just unreadable gibberish with no discernable pattern to unauthorized users.

Cheung says that binary Goppa code encryption that can resist quantum hacking can be deployed right now on the same servers and infrastructure that agencies are already using. It would just be a matter of switching things over to the new method. With quantum computers evolving and improving so rapidly these days, Cheung believes that there is little time to waste.

Yes, making the switch in encryption methods will be a little bit of a chore, he said. But with new developments in quantum computing coming every day, the question is whether you want to maybe deploy quantum-resistant encryption two years too early, or risk installing it two years too late.

John Breeden II is an award-winning journalist and reviewer with over 20 years of experience covering technology. He is the CEO of the Tech Writers Bureau, a group that creates technological thought leadership content for organizations of all sizes. Twitter: @LabGuys

Read more:
Is Now the Time to Start Protecting Government Data from Quantum Hacking? - Nextgov

The growing need for encrypted communications – TechRadar

Nowadays most of our communication is conducted online using messaging apps and services on our smartphones and computers. However, ensuring our messages remain private and secure has become increasingly difficult which is why business users and consumers alike are now turning to encrypted messaging apps.

At the same time though, the intelligence-sharing alliance Five Eyes and other national governments continue to call on tech companies to create backdoors which would give them access to users end-to-end encrypted communications. This would defeat the purpose of using encrypted messaging apps and services in the first place and put the security and privacy of users worldwide at risk.

To learn more about the benefits of encrypted messaging and how these tools can benefit remote workers, TechRadar Pro spoke with the co-founder and CTO of Wickr Chris Howell.

As a class, they represent the state of the art in privacy and security. The biggest thing end-to-end encryption (E2EE) does is it takes the app or service provider out of the equation from a message privacy perspective. If the service providers systems cant read your messages, then neither can one of their rogue employees or someone who manages to compromise their servers.

For one thing, the line between business and personal isnt so clear now that people are all reachable 24/7. Personal business is just as important as company business to most of us. Both aspects have suffered equally due to the industrys failure to provide meaningful security for communications applications over the years. E2EE was first popularized in consumer apps, and its only because it was so easy to use there that the demand for business use grew and more enterprise-grade tools like Wickr evolved.

Simply ensuring that data is always encrypted doesnt count. It has to be a form of encryption that cant be decrypted by anyone or anything other than the sender and receiver. If any system or device in the message delivery path between the sender and receiver can decrypt and read it (and use of technologies like HTTPS or TLS is a dead giveaway for this), its not E2EE.

The U.S. Air Force has a particularly strong vision to offer the warfighter a highly secure collaboration solution that can support the mission all the way out to the tactical edge. Of course, there are some specialized use cases out there, but at a base level, the military needs the same thing we all need - an easy to use unified communications tool they can count on to secure their sensitive communications.

Weve been fortunate in the past year or so to add smart folks like Blake and others to the team who bring with them decades of military experience from headquarters to harm's way. If were going to serve the warfighter, wed better understand what our product needs to meet the mission, how it will be used and on what systems, and how it will be tested, deployed and scaled. Their perspective is invaluable and is really helping us make our product the best it can be.

Most people are still shocked at just how insecure the communication tools we grew up on have always been. To some extent, the tide is turning, and I think more and more, the expectation will be that our communications - business or private - should be secure vs. the alternative. Demand in business will especially grow as private business is increasingly faced with more advanced threats, including international organized criminal hacking groups and even nation-states. The fact that E2EE solutions like ours can also now support regulatory compliance/message archival regimes and operate at an enterprise-scale has contributed to its growth as well.

More people working from home means more sensitive business is being conducted in virtual versus traditional conference rooms. The more we shift to virtual, the more data thats at risk to remote attackers. We saw it play out in the scramble to remote conferencing solutions last spring. Not long after the scramble came the uptick in security incidents as attackers exploited the weaknesses in solutions that frankly werent suited for many of the use cases being thrust upon them. The ordeal of the past year educated a lot of people in the importance of secure communications.

The main thing to keep in mind is different services offer different levels of protection. Most services will say they are secure and encrypted, but virtually all of them still have access to your data, I.e., are not E2EE. More and more services are seeing the light and adding E2EE, which is great, but not everyone can do it well, and theres more to security than just plugging in an encryption library. If security is an important requirement, make sure its even more important in the eyes of the service provider. It takes more than a checkbox to do it right.

See the original post here:
The growing need for encrypted communications - TechRadar

NordVPN review: An encryption powerhouse with the biggest VPN bang for your buck – CNET

NordVPN stays on our list of best 2020 mobile VPNs for many reasons, including its status as the reigning champion of the bang-for-buck ratio. Hands down, you aren't going to get a VPN anywhere else that can do more than NordVPN does, as cheaply as NordVPN does it. Despite a security breach reported in 2019 (more on that below), you'd still be hard pressed to find another VPN that can do what NordVPN does at all.

Sure, NordVPN could offer a little more privacy if it boosted the number of servers it owns, but we're talking about over 5,300 servers in 59 countries, a zero-log policy and a jurisdiction in Panama. It's an encryption powerhouse, and has a feature that allows you to VPN into Tor.

It's no surprise NordVPN racked up more than 59,000 ratings in the App Store for a score of 4.6 out of 5, and 132,871 reviews in the Google Play Store for a 4.4 out of 5 rating. Also no surprise it's snagged my trophy for best value.

As a speed bonus, NordVPN's SmartPlay feature lets it do with ease what so many other VPNs struggle with: streaming video. It's available for not only iOS and Android, but also Windows Phone and even BlackBerry.

Read more:How we review VPNs

We ran our NordVPN speed tests over the course of three days using both wireless and Ethernet connections. Internet speeds in the US vary widely by state and provider. And with any speed test, results are going to rely on your local infrastructure, with hyperfast internet service yielding higher test speed results.

That's one reason we're more interested in the amount of speed lost, as the use of any VPN can typically cut your internet speed by half or more. NordVPN reduced our speeds by 53% on average, compared to the 32% speed loss we measured when we tested it in 2019. While not as fast as some of its competitors like ExpressVPNand Surfshark, we found that NordVPN's speeds were reliably fast; there were never any sudden dips or service interruptions, and where we expected it to underperform, it proved itself up to the task.

NordVPN's overall global average speed was 91Mbps during my testing, in a dataset with average non-VPN speeds of 194Mbps. While it's normal for a VPN to cut your internet speed by half or more, the notable context here is that across the averages of my five test zones, I never saw NordVPN fall below 85Mbps. It's still one of the most consistent, stable VPNs I've worked with.

Singapore led the testing averages at 98Mbps, while UK speeds beat European speeds by a hair's breadth. At 99.93Mbps, UK connections squeaked ahead of French and German ones, which averaged 91.90Mbps. NordVPN also had another photo finish during testing, with Australia beating US scores, 88Mbps to 86Mbps. None of these are scores that you can look down your nose at.

Read more: All the VPN terms you need to know

We like that NordVPN is headquartered in Panama, which is generally considered a privacy-friendly country due to its lack of surveillance-sharing agreements with other countries.

Its encryption is standard AES-256-CBC, and it supports Perfect Forward Secrecy, which means it frequently changes encryption keys to avoid security compromises. NordVPN also uses OpenVPN protocol (one of the most secure protocols available) and IPSec/IKEv2 (which is less secure but still quite fast). No IP address, DNS or other potentially user-identifying data leaks were detected during our testing.

The company offers a useful kill switch feature, which prevents network data from leaking outside of its secure VPN tunnel in the event the VPN connection fails. Those unfamiliar with the software should note the additional customizable kill switch that allows you to select which apps to kill in the event of a VPN drop-out. Keep in mind that any apps not on that list will still transmit information over the internet and could therefore become a privacy liability.

Additional features include a site filter to block out a broader swath of malicious sites, along with optional ad and tracker blocker. The latter goes a long way toward keeping speeds up for the average user. We also like Nord's double VPN feature, which allows users to leap across multiple servers for a bit of extra encryption. And we found its obfuscation (the process of making a VPN not look like a VPN) effective in every instance of testing.

While NordVPN has lived on our list of recommended vendors for a long time, we moved it to the penalty box in October 2019 to re-evaluate our recommendation after a report emerged that one of its rented servers was accessed without authorization in 2018. Nord's actions following the discovery included -- eventually -- multiple security audits, a bug bounty program and heavier investments in server security.

While we'd have preferred that Nord self-disclosed the issue much earlier, the fact that the breach was very limited in nature and involved no user-identifying information served to further verify that NordVPN keeps no logs of user activity. And NordVPN's subsequent move to full RAM-disk use -- meaning it's not storing anything on hard drives -- as a breach response went a long way toward convincing us of the company's security commitment. As a result, Nord remains on our list of recommended vendors.

Read more: After the breach, Nord is asking people to trust its VPN again

We like NordVPNs clean, easy-to-use interface, its toggle controls, and its server search functions. The interactive map graphic is pleasant in design, but could be made more useful if its default setting identified cities instead of only the countries.

NordVPN offers 24/7 customer service support through live chat, with an email option. It also has a well-built support section on its website, which contains a veritable library of FAQs and tutorials.

NordVPN imposes no data caps and allows unlimited server switching and torrenting. We had no problems using it to access Netflix. Unlike some competitors, however, you can only run six devices simultaneously on a single subscription.

Since the world of VPNs moves at a fast pace, we'd prefer to see NordVPN's steep discounts applied laterally toward all of its contracts in order to report better overall purchasing value. That would be a sharper criticism if NordVPN wasn't already a long-standing industry leader with a lengthy history, and it's certainly a criticism that could be applied to nearly all VPN providers. As it stands, its best deal is via its two-year contract at $3.71 per month, a 68% discount, billed once every two years for $89. NordVPN does offer a 30-day money-back guarantee, however.

While NordVPN no longer accepts PayPal payments, you can pay with a credit card or cryptocurrency including Bitcoin, AliPay, WeChat Payments, iTunes, Google Pay, Amazon Pay and UnionPay.

Discover the latest apps: Be the first to know about the hottest new apps with the CNET Apps Today newsletter.

Now playing: Watch this: Top 5 reasons to use a VPN

2:42

See original here:
NordVPN review: An encryption powerhouse with the biggest VPN bang for your buck - CNET

Global Encryption Software Market Projected to Reach USD XX.XX billion by 2025: Dell , Eset , Gemalto , IBM , Mcafee , Microsoft – TechnoWeekly

Global Encryption Software Market: Introduction

The recently added research report has been meticulously conceived and presented to render a pin-point analytical review of the current market conditions. This intensive research report on Global Encryption Software Market has been recently added to the burgeoning repository to evaluate the market growth forces on a multi-dimensional and multi-faceted approach. This well-conceived research report presentation portrays market dynamics through the entire growth tenure, 2020-27.

Readers in the course of the study are offered decisive access to multi-faceted market forces at play to harness indomitable growth trail across high intensity competitive landscape in global Encryption Software market.

Key Market Player Analysis: Global Encryption Software Market:DellEsetGemaltoIBMMcafeeMicrosoftPkwareSophosSymantecThales E-SecurityTrend MicroCryptomathicStormshield

This report on global Encryption Software market includes a detailed overview of all the prominent players in the competitive landscape, with elaborate details also of other contributing players as well as investors eying for seamless penetration in the competitive isle.

The report covers a thorough overview section inclusive of relevant details pertaining to company profiles, production and consumption ratios, production capacities, revenue generation cycles, gross pricing as well as product specificities and major growth catalysts that collectively create ample opportunities to drive million dollar growth in global Encryption Software market.

Regional Overview: Global Encryption Software MarketA thorough evaluation and assessment study of growth prospects through the forecast spam, 2020-25 has also been significantly included in this report. Proceeding beyond regional scope, country specific analysis with prime identification of production and consumption channels, logistics, investor preferences besides vendor activities have been discussed at length in this report, committed to encourage vendor specific business decisions, eying steady and strong foothold in the competition spectrum.

The report includes a dedicated section on market segmentation with veritable references on product type, usability, as well as end-use applications and versatility that collectively instigate optimistic growth scenario in global Encryption Software market.

Access Complete Report @ https://www.orbismarketreports.com/global-encryption-software-market-size-status-and-forecast-2019-2025-2?utm_source=Puja

Segmentation by Type: Based on elaborate sections described and decoded in the report, readers are equipped with tangible insights on various product categories, inclusive of their performance and systematic improvisation to sui industry protocols and end user expectations.On-premisesCloud

Segmentation by Application: Through this part of the report, readers, market participants and stakeholders are offered tremendous investment guidance to identify the potential of the segment in instigating desired customer response, and eventual revenue generation tendencies.Disk encryptionFile/folder encryptionDatabase encryptionCommunication encryptionCloud encryption

The key regions covered in the Encryption Software market report are:North America (U.S., Canada, Mexico)South America (Cuba, Brazil, Argentina, and many others.)Europe (Germany, U.K., France, Italy, Russia, Spain, etc.)Asia (China, India, Russia, and many other Asian nations.)Pacific region (Indonesia, Japan, and many other Pacific nations.)Middle East & Africa (Saudi Arabia, South Africa, and many others.)

This section of the report lends exclusive focus in assessing various regional and country specific elements of the Encryption Software market. Besides segregating the growth hotspots, this section embodies versatile understanding concerning various growth harnessing industrial practices as well as strategic aid favoring uncompromised growth and sustainable revenue returns in global Encryption Software market.

Scope of the ReportThe discussed Encryption Software market has been valued at xx million US dollars in 2020 and is further projected to grow at xx million US dollars through the forecast span till 2026, growing at a CAGR of xx% through the forecast period.

Place Inquiry for Buying or Customization of [emailprotected] https://www.orbismarketreports.com/enquiry-before-buying/66445?utm_source=Puja

Key Report Offerings: The report is a thoroughly dependable resource guide to understand dynamic market segments operational in the market, as well as their subsequent growth rendering potential. A close review of various growth kindling and limiting factors maneuvering growth The report makes substantial forecast predictions for 5-7 years growth likelihood and associated developments The report proceeds with unraveling crucial market specific information in the realms of competition intensity and dynamics besides identifying major players

(*If you have any special requirements, please let us know and we will offer you the report as you want.)

About Us : Our team of expert research professionals are committed to offering high-end industry-specific critical reports inclusive of high accuracy insights for future-ready business discretion. Our commitment of unbiased research has enabled a thorough evaluation process of voluminous data to infer market-relevant derivation.

Contact Us : Hector CostelloSenior Manager Client Engagements4144N Central Expressway,Suite 600, Dallas,Texas 75204, U.S.A.Phone No.: USA: +1 (972)-362-8199 | IND: +91 895 659 5155

Read more here:
Global Encryption Software Market Projected to Reach USD XX.XX billion by 2025: Dell , Eset , Gemalto , IBM , Mcafee , Microsoft - TechnoWeekly