Single Column Posts

3 min read

Jeff Horn and Tim Tszyu will be aired live in the United States, as ESPN+ have picked up the fight, which will stream at 5...

5 min read

Indy 500 live: In a normal season is that the finale of what is commonly known as the Month of May in IndyCar racing. The...

4 min read

PSG vs RB Leipzig Live :Are two clubs which have made many enemies among football fans, but maybe not to the way they playwith. On...

4 min read

RB Leipzig v Paris Saint-Germain live stream: How to watch Champions League clash for free – kick-off time, TV Channel and radio coverage.Semifinals start Tuesday...

4 min read

Nets vs Raptors live :After two weeks of seeding games, the action inside the bubble at Disney World will continue with the 2020 NBA Playoffs....

3 min read

Raptors vs Nets Live : After Fourteen Days of seeding Matches, the action in the bubble at Disney World will last using the 2020 NBA...

4 min read

The Utah Jazz do Not have a Solid track record Contrary to the Denver Nuggets this season. Denver won all three matchups this season, all...

5 min read

Barcelona player talks about tonight's Champions League quarter-final against his former club Bayern Munich. The midfielder is well-known for his self-sacrificing style of drama and...

5 min read

Present Barcelona player talks about tonight's Champions League quarter-final against his former team -- Bayern Munich. The midfielder is well-known for his self-sacrificing style of...

6 min read

Current Barcelona player talks about tonight's Champions League quarter-final against his former team -- Bayern Munich. The midfielder is well known for his self-sacrificing manner...

September 29, 2020

The Post Wired

News On Trending

Intel, Microsoft’s ‘picture-great’ answer for dangers on your gadgets

Spread the love

Researchers from Intel and Microsoft are working together to study new applications of deep learning for classifying malware, said Microsoft in a blog post. “The basis for this study is the observation that if malware binaries are plotted as grayscale images, the textural and structural patterns can be used to effectively classify binaries as either benign or malicious, as well as cluster malicious binaries into respective threat families,” said the company.

Their research project, called STAMINA (STAtic Malware-as-Image Network Analysis, which has been found to achieve high accuracy in detecting malware with low false positives.

Microsoft explains that through this analysis, metadata is produced, which is analysed by machine learning classifiers on the client and in the cloud to determine whether a file is malicious. Use of static analysis approach is said to catch most threats before they can even run.

As part of this research project, the companies adopted a three-step approach — image conversion, transfer learning, and evaluation.

Firstly, the researchers prepared the binaries by converting them into two-dimensional images through a process that involves pixel conversion, reshaping, and resizing. The second step was to use transfer learning, a technique for overcoming the isolated learning paradigm and utilizing knowledge acquired for one task to solve related ones. Finally, the performance of the system was measured and reported on the holdout test set.

In its findings, the companies found that applying STAMINA achieved 99.07% accuracy at 2.58% false positive rate overall.

“The results certainly encourage the use of deep transfer learning for the purpose of malware classification,” said Jugal Parikh and Marc Marino, researchers from Microsoft Threat Protection Intelligence Team. “The use of deep learning methods for detecting threats drives a lot of innovation across Microsoft. The collaboration with Intel Labs researchers is just one of the ways in which Microsoft researchers and data scientists continue to explore novel ways to improve security overall,” they added.