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

12/3/2020
12:40 PM
Connect Directly
Twitter
RSS
E-Mail
50%
50%

Researchers Bypass Next-Generation Endpoint Protection

Machine learning-based products can be tricked to classify malware as a legitimate file, new findings show.

Just because your endpoint security product employs machine learning (ML) doesn't mean it can't be manipulated to miss malware, new research shows.

A pair of researchers will demonstrate at Black Hat Europe next week how they were able to bypass ML-based, next-generation anti-malware products. Unlike previous research that reverse-engineered the next-generation endpoint tool — such as Skylight's bypass of Cylance's endpoint product in 2018 — the researchers instead were able to cheat the so-called static analysis malware classifiers used in some next-gen anti-malware products without reverse engineering them.

They first tested their attacks using the open source, static malware-classifier tool Ember, and then were able to take that attack and use it against several next-gen antivirus (AV) products, which they declined to name. The research advances findings they presented in September at the International Joint Conference on Neural Networks (IJCNN).

They sneaked known malware samples past the products by modifying some of the exploit file's features, such as checksums and time stamps, which allowed them to fool the static classifier into believing the malware was made up of legitimate files and not malicious. (The malware classifier basically determines whether a binary file contains malware.)

"It was part of research we were doing to protect our own product — to assess the vulnerability of next-generation antivirus to different forms of attack," says Ishai Rosenberg, head of the deep learning group at Deep Instinct.

Related Content:

How to Secure Machine Learning

The Changing Face of Threat Intelligence

New on The Edge: Loyal Employee ... or Cybercriminal Accomplice?

"We tried to show that there are other techniques" for bypassing next-gen AV that don't require reverse-engineering the endpoint protection system, he says.

Rosenberg's colleague Shai Meir, security researcher and data scientist in deep learning at Deep Instinct, says they only slightly modified features of the malware samples, and that was all it took for the classifier in the next-gen AV systems to label the code as benign and not malicious.

"We [first] started attacking those features and seeing how the classifier scores the changes" in them, Meir explains. "For example, a change in the time-stamp signature of a file could affect the score" and make it look benign, he says.

They say the attack could be pulled off easily, but defending against it is difficult. "There is no silver bullet," Meir says. Protection requires defense in depth, he says, but even that is no guaranteed prevention technique.

"This is a generic problem from machine learning" and falls into the category of adversarial ML, Rosenberg notes.

Adversarial ML seems a long way off to many businesses. But even ML-based security tools are susceptible to these types of attacks.

"Watch out for this thing because [it is] coming, and as a vendor and an organization, you should be prepared," Rosenberg warns.

Kelly Jackson Higgins is the Executive Editor of Dark Reading. She is an award-winning veteran technology and business journalist with more than two decades of experience in reporting and editing for various publications, including Network Computing, Secure Enterprise ... View Full Bio
 

Recommended Reading:

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
News
Former CISA Director Chris Krebs Discusses Risk Management & Threat Intel
Kelly Sheridan, Staff Editor, Dark Reading,  2/23/2021
Edge-DRsplash-10-edge-articles
Security + Fraud Protection: Your One-Two Punch Against Cyberattacks
Joshua Goldfarb, Director of Product Management at F5,  2/23/2021
News
Cybercrime Groups More Prolific, Focus on Healthcare in 2020
Robert Lemos, Contributing Writer,  2/22/2021
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win an Amazon Gift Card! Click Here
Latest Comment: "The truth behind Stonehenge...."
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
Building the SOC of the Future
Building the SOC of the Future
Digital transformation, cloud-focused attacks, and a worldwide pandemic. The past year has changed the way business works and the way security teams operate. There is no going back.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2021-27886
PUBLISHED: 2021-03-02
rakibtg Docker Dashboard before 2021-02-28 allows command injection in backend/utilities/terminal.js via shell metacharacters in the command parameter of an API request. NOTE: this is NOT a Docker, Inc. product.
CVE-2016-8153
PUBLISHED: 2021-03-02
** REJECT ** DO NOT USE THIS CANDIDATE NUMBER. ConsultIDs: none. Reason: The CNA or individual who requested this candidate did not associate it with any vulnerability during 2016. Notes: none.
CVE-2016-8154
PUBLISHED: 2021-03-02
** REJECT ** DO NOT USE THIS CANDIDATE NUMBER. ConsultIDs: none. Reason: The CNA or individual who requested this candidate did not associate it with any vulnerability during 2016. Notes: none.
CVE-2016-8155
PUBLISHED: 2021-03-02
** REJECT ** DO NOT USE THIS CANDIDATE NUMBER. ConsultIDs: none. Reason: The CNA or individual who requested this candidate did not associate it with any vulnerability during 2016. Notes: none.
CVE-2016-8156
PUBLISHED: 2021-03-02
** REJECT ** DO NOT USE THIS CANDIDATE NUMBER. ConsultIDs: none. Reason: The CNA or individual who requested this candidate did not associate it with any vulnerability during 2016. Notes: none.