Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Endpoint Security

7/26/2017
03:58 PM
Curtis Franklin
Curtis Franklin
Curt Franklin
50%
50%

Researchers Bring AI to Endpoint Security

FFRI has an AI approach to malware defense - and it will protect systems with no Internet connection at all.

In the era of Skype and Facetime, it's easy for introverts (and CFOs) to ask why face-to-face events like Black Hat are still important. I've asked similar questions myself but ten minutes at Black Hat provided multiple examples of the value a gathering still possesses. On my way to the media center I had two research reports pressed into my hands (you'll hear more about at least one of them before I leave the conference), had lined up two guests for future episodes of Voice of Security Radio, and had pretty much filled my schedule for the rest of the week.

And that's before I grabbed my first cup of coffee.

Once I sat down, the encounters continued. One of the first was with Yuji Ukai and Pablo Garcia of Fourteenforty Research Institute, which is more commonly known as FFRI, Inc. Yuji is well known in the security research community, serving on the review board for presentations at Black Hat.

Ukai and Garcia met as technical staff members at eEye and are now at FFRI, where Ukai is CEO and Garcia is CEO of FFRI Americas. FFRI is in the business of data security and attack prevention. Their product, yarai, is an AI-based malware prevention program that runs entirely in software on the endpoint. When I talked with Ukai about the software, he told me that the artificial intelligence algorithms used in the software are a direct result of the research he and his team do into malware and vulnerability exploitation.

Most of the conversation, in fact, was about research -- it's obvious that the research side is where Ukai's passion lies. In taking the research to market, they decided to go with protection rather than becoming a pure security research and consulting firm. Garcia pointed out that the AI basis means that the client software can run on an entirely air-gapped computer; there's no need for regular network connection for updating signatures or using cloud-based analysis.


Want to learn more about the technology and business opportunities and challenges for the cable industry in the commercial services market? Join Light Reading in New York on November 30 for the 11th annual Future of Cable Business Services event. All cable operators and other service providers get in free.

yarai has been available to large enterprise customers in Japan for more than four years and is now expanding into the North American through the third-party channel of resellers and integrators. From a technology perspective, yarai is interesting because it's an example of machine intelligence applied to security. In conversation after conversation the phrases "machine learning" and "artificial intelligence" come up when applied to security, but they're often mentioned in terms of rapid response to alerts.

Malware protection has traditionally been based on either signature matching or heuristics, which often takes the form of fuzzy behavior-based pattern matching. Genuine AI is still relatively rare in the endpoint security space; still less common are such products and services coming from a security research team.

There's plenty more to come from Black Hat -- refresh the home page often and watch my twitter feed (@kg4gwa) for more news.

— Curtis Franklin is the editor of SecurityNow.com. Follow him on Twitter @kg4gwa.

Comment  | 
Print  | 
More Insights
Comments
Oldest First  |  Newest First  |  Threaded View
Edge-DRsplash-10-edge-articles
7 Old IT Things Every New InfoSec Pro Should Know
Joan Goodchild, Staff Editor,  4/20/2021
News
Cloud-Native Businesses Struggle With Security
Robert Lemos, Contributing Writer,  5/6/2021
Commentary
Defending Against Web Scraping Attacks
Rob Simon, Principal Security Consultant at TrustedSec,  5/7/2021
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
2021 Top Enterprise IT Trends
We've identified the key trends that are poised to impact the IT landscape in 2021. Find out why they're important and how they will affect you today!
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2021-22152
PUBLISHED: 2021-05-13
A Denial of Service due to Improper Input Validation vulnerability in the Management Console component of BlackBerry UEM version(s) 12.13.1 QF2 and earlier and 12.12.1a QF6 and earlier could allow an attacker to potentially to prevent any new user connections.
CVE-2021-22153
PUBLISHED: 2021-05-13
A Remote Code Execution vulnerability in the Management Console component of BlackBerry UEM version(s) 12.13.1 QF2 and earlier and 12.12.1a QF6 and earlier could allow an attacker to potentially cause the spreadsheet application to run commands on the victim’s local machine with t...
CVE-2021-22154
PUBLISHED: 2021-05-13
An Information Disclosure vulnerability in the Management Console component of BlackBerry UEM version(s) 12.13.1 QF2 and earlier and 12.12.1a QF6 and earlier could allow an attacker to potentially gain access to a victim's web history.
CVE-2021-20331
PUBLISHED: 2021-05-13
Specific versions of the MongoDB C# Driver may erroneously publish events containing authentication-related data to a command listener configured by an application. The published events may contain security-sensitive data when commands such as "saslStart", "saslContinue", "i...
CVE-2021-31215
PUBLISHED: 2021-05-13
SchedMD Slurm before 20.02.7 and 20.03.x through 20.11.x before 20.11.7 allows remote code execution as SlurmUser because use of a PrologSlurmctld or EpilogSlurmctld script leads to environment mishandling.