News
HGP – First Next Gen machine learning engine to identify malware
Fairfax, VA, August 25, 2016 – Invincea, the leader in machine learning for endpoint protection, announced today that its deep learning model for analyzing unknown malware is now fully integrated in the VirusTotal site. VirusTotal is a “service that analyzes suspicious files and URLs and facilitates the quick detection of viruses, worms, Trojans, and all kinds of malware”[1].By integrating with VirusTotal, Invincea is pushing machine learning into mainstream cyber security solutions. By participating in the VirusTotal community, Invincea is continuing to fulfill their three key principles to security market transparency and accountability: participate in independent 3rd party testing, work towards commonly accepted standards, and avoid being a black box. As part of these principles, Invincea became one of the first next gen endpoint security companies to join the Anti-Malware Testing Standards Organization (AMTSO) in June. Invincea was also the only next generation endpoint security firm to participate in 3rd party testing by AV-TEST so far this year. Finally, Invincea publishes its machine learning approach in peer-reviewed academic conferences and industry tradeshows including BlackHat. Agreeing to the AMTSO principles and test methodologies, as well as being tested by approved 3rd parties is required to be listed on VirusTotal. X by Invincea was recently tested and certified by AV-TEST.
“AMTSO was founded to improve the quality of anti-malware testing methodologies. We applaud vendors like Invincea who work with the community to increase transparency and advance our industry standards.” said Dennis Batchelder, General Manager of AMTSO.
Invincea is the first machine learning solution to be listed on VirusTotal, which in addition to determining whether the file is likely malicious, provides the malware family to which the program likely belongs. While other machine learning approaches can score a file based on its confidence, X by Invincea can determine the malware family provenance of the file—a capability enabled by its deep learning algorithms developed under DARPA-funded research. This additional malware provenance is particularly useful for malware analysts who not only want to know whether the file is malicious or not, but also what kind of malware they are dealing with. The results from Invincea’s deep learning model, embedded as one component in its X by Invincea product, will be listed side-by-side with the traditional antivirus engines already listed by VirusTotal.
The deep learning model that powers X by Invincea was built based on years of research in Invincea Labs supported by DARPA funding — the US government agency working on breakthrough technologies for national security. Using this technology, X can determine if a file is malicious, even if that file has never been seen before and does not have a known signature.
About Invincea: Invincea is a machine learning endpoint security software company dedicated to killing threats without impacting business performance. More than 25,000 customers rely on Invincea to prevent and detect threats and enable their workforce to conduct business—in the office or on the road. Only X by Invincea comes with Performance-Built-InTM, which combines machine learning and behavioral monitoring to eliminate endpoint security blind spots without sacrificing usability. With Invincea, your workforce won’t know it’s there, but you will. The company is venture capital-backed and based in Fairfax, VA. For more information, visit www.invincea.com.
To view the full article, please click here.