Vulnerabilities / Threats

7/25/2017
10:00 AM
Connect Directly
Twitter
Twitter
RSS
E-Mail
100%
0%

Using AI to Break Detection Models

Pitting machine learning bots against one another is the new spy vs. spy battle in cybersecurity today.

In the spy versus spy world that pits cybersecurity defense against money-motivated attackers, it always pays to think a few steps ahead of the attackers. Any security pro who has seen the direction that detection is going these days with artificial intelligence and machine learning understands that those next attacks steps are probably going to involve some sort of subversion of the AI algorithms. If security wants to effectively use AI, it will need to find ways to harden those models

This week at Black Hat, one researcher hopes to contribute to the discipline by showing off a new automated AI agent that probes the data science behind machine learning malware detection models and looks for mathematical weaknesses.

"All machine learning models have blind spots. All of them. And a sophisticated and motivated adversary is out there trying to exploit them," says Hyrum Anderson, technical director of data science for Endgame. "We have created an artificial agent that tries to automatically discover those blind spots."

As he puts it, the agent "literally plays a game against our model and tries to beat it," essentially automating the auditing of the mathematical underpinning of detection mechanisms. The agent essentially inspects an executable file and uses a sequence of file mutations to test the detection model. This agent uses its own brand of machine learning to figure out which sequences of mutations are most likely to create a variant that evades the model. Using the information it gains from this automated test, the agent can create a policy for developing malware variants that have a high likelihood of breaking the opposing machine learning model of the detection engine.

This is the logical next step in advancement of thought about cybersecurity's auditing of machine learning efficacy, and one which Anderson hopes to encourage across the industry as vendors further refine their machine learning mechanisms. 

"You'll get no criticisms from me (about the competition). I think in general my colleagues and competitors are all paranoid and are always thinking about how to make (their models) secure. But that's usually a manual process. It's spot-checking and it's somebody looking at it," he says. "We wanted to take that to the next level. I don't believe that our adversaries are yet using this level of sophistication we are proposing in our research, but that's the point. We want to get there before they do."

At the moment, Anderson's use of the agent begins and ends with Endgame's own machine learning model. But, in concert with his presentation, he and his team are going to release code that is generic and adaptable for other vendors and researchers to inspect their own models. 

"We want to put it out there because a rising tide raises all boats," Anderson says.

The idea of machine learning and AI hardening is generally gaining momentum with data scientists and security specialists of late. In fact, this is one of several talks at Black Hat this year that will focus on problems that can arise through flawed machine learning algorithms. For example, in one talk a data scientist with Sophos will discuss how bad data can screw up detection models. Another from a group of Georgia Tech researchers will dive into a new tool that aims to sabotage detection mechanisms in Android antivirus apps. 

 

Related Content:

Ericka Chickowski specializes in coverage of information technology and business innovation. She has focused on information security for the better part of a decade and regularly writes about the security industry as a contributor to Dark Reading.  View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
Crowdsourced vs. Traditional Pen Testing
Alex Haynes, Chief Information Security Officer, CDL,  3/19/2019
New Mirai Version Targets Business IoT Devices
Dark Reading Staff 3/19/2019
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: Reading Schneier's Friday Squid Blog again?
Current Issue
5 Emerging Cyber Threats to Watch for in 2019
Online attackers are constantly developing new, innovative ways to break into the enterprise. This Dark Reading Tech Digest gives an in-depth look at five emerging attack trends and exploits your security team should look out for, along with helpful recommendations on how you can prevent your organization from falling victim.
Flash Poll
The State of Cyber Security Incident Response
The State of Cyber Security Incident Response
Organizations are responding to new threats with new processes for detecting and mitigating them. Here's a look at how the discipline of incident response is evolving.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2019-6149
PUBLISHED: 2019-03-18
An unquoted search path vulnerability was identified in Lenovo Dynamic Power Reduction Utility prior to version 2.2.2.0 that could allow a malicious user with local access to execute code with administrative privileges.
CVE-2018-15509
PUBLISHED: 2019-03-18
Five9 Agent Desktop Plus 10.0.70 has Incorrect Access Control (issue 2 of 2).
CVE-2018-20806
PUBLISHED: 2019-03-17
Phamm (aka PHP LDAP Virtual Hosting Manager) 0.6.8 allows XSS via the login page (the /public/main.php action parameter).
CVE-2019-5616
PUBLISHED: 2019-03-15
CircuitWerkes Sicon-8, a hardware device used for managing electrical devices, ships with a web-based front-end controller and implements an authentication mechanism in JavaScript that is run in the context of a user's web browser.
CVE-2018-17882
PUBLISHED: 2019-03-15
An Integer overflow vulnerability exists in the batchTransfer function of a smart contract implementation for CryptoBotsBattle (CBTB), an Ethereum token. This vulnerability could be used by an attacker to create an arbitrary amount of tokens for any user.