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.

Threat Intelligence

6/13/2017
06:15 PM
Connect Directly
Twitter
LinkedIn
Google+
RSS
E-Mail
50%
50%

How Bad Data Alters Machine Learning Results

Machine learning models tested on single sources of data can prove inaccurate when presented with new sources of information.

The effectiveness of machine learning models may vary between the test phase and their use "in the wild" on actual consumer data.

Many research papers claim high rates of malware detection and false positives with machine learning, and often deep learning, models. However, nearly all of these rates are within the context of a single source of data, which authors use to train and test their models.

Machine learning has become more advanced but isn't used enough yet in security, says Hillary Sanders, data scientist for Sophos' data science research group. She anticipates usage will increase in coming years to address the rise of different forms of malware.

Historically, Sanders explains, static signatures have been used to detect malware. This method doesn't scale well because software needs to be updated with new signatures as more malware is created. Machine learning and deep learning automatically generate more flexible patterns, which could better detect malicious content compared with stricter static signatures.

"This enables us to move away from signature detection and more toward deep learning detection, which doesn't really require signatures and is going to be better at detecting malware that has never been seen before," she says.

The challenge is in creating a deep learning model to detect forms of malware that don't yet exist. Sanders explains the problem of using current data to test these models, which would ideally be used to detect future malware strains in different clients and environments.

"We can't be sure the data we trained on is going to be super similar to the data in organization deployment," she explains. "If we're training on data that isn't like the data we want to eventually test on, our model might fail catastrophically."

In current machine learning research, accuracy estimates don't consider how systems will process future data. Sanders says modern publications lack time-decay analysis and sensitivity analysis, which could lead to a lack of trust among those who rely on this information.

"If researchers forget to focus on sensitivity testing and time decay, our models are liable to fail catastrophically in the wild," she explains.

Time-decay analysis simulates how the accuracy of data decreases over time, she explains. Consider a dataset with information from January through April. If a machine learning model is trained on data before February 1, it will do well on processing data from January, but accuracy will begin to decay after February.

Sensitivity analysis tweaks inputs for machine learning models to see how output is affected. Sanders will present sensitivity results in her presentation titled "Garbage In Garbage Out: How Purportedly Great Machine Learning Models Can Be Screwed Up By Bad Data" at this year's Black Hat USA conference in Las Vegas.

This analysis will include a deep learning model designed to detect malicious URLs, which was trained and tested using three sources of URL data. As part of her discussion, she'll dive into what caused the results by focusing on how the data sources are different, and higher-level feature activations the neural net identified in some datasets but not in others.

For security teams, the end goal with deep learning is to stop malware. If training and testing data is biased compared with real-world data, models are likely to miss out.

"You ignore the thing you could be optimizing for," says Sanders. "You could miss swaths of malware."

Black Hat USA returns to the fabulous Mandalay Bay in Las Vegas, Nevada, July 22-27, 2017. Click for information on the conference schedule and to register.

 

Related Content:

Kelly Sheridan is the Staff Editor at Dark Reading, where she focuses on cybersecurity news and analysis. She is a business technology journalist who previously reported for InformationWeek, where she covered Microsoft, and Insurance & Technology, where she covered financial ... View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
Why Cyber-Risk Is a C-Suite Issue
Marc Wilczek, Digital Strategist & CIO Advisor,  11/12/2019
DevSecOps: The Answer to the Cloud Security Skills Gap
Lamont Orange, Chief Information Security Officer at Netskope,  11/15/2019
Attackers' Costs Increasing as Businesses Focus on Security
Robert Lemos, Contributing Writer,  11/15/2019
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: This comment is waiting for review by our moderators.
Current Issue
Navigating the Deluge of Security Data
In this Tech Digest, Dark Reading shares the experiences of some top security practitioners as they navigate volumes of security data. We examine some examples of how enterprises can cull this data to find the clues they need.
Flash Poll
Rethinking Enterprise Data Defense
Rethinking Enterprise Data Defense
Frustrated with recurring intrusions and breaches, cybersecurity professionals are questioning some of the industrys conventional wisdom. Heres a look at what theyre thinking about.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2014-5118
PUBLISHED: 2019-11-18
A Security Bypass Vulnerability exists in TBOOT before 1.8.2 in the boot loader module when measuring commandline parameters.
CVE-2019-12422
PUBLISHED: 2019-11-18
Apache Shiro before 1.4.2, when using the default "remember me" configuration, cookies could be susceptible to a padding attack.
CVE-2012-4441
PUBLISHED: 2019-11-18
Cross-site Scripting (XSS) in Jenkins main before 1.482 and LTS before 1.466.2 allows remote attackers to inject arbitrary web script or HTML in the CI game plugin.
CVE-2019-10764
PUBLISHED: 2019-11-18
In elliptic-php versions priot to 1.0.6, Timing attacks might be possible which can result in practical recovery of the long-term private key generated by the library under certain conditions. Leakage of a bit-length of the scalar during scalar multiplication is possible on an elliptic curve which m...
CVE-2019-19117
PUBLISHED: 2019-11-18
/usr/lib/lua/luci/controller/admin/autoupgrade.lua on PHICOMM K2(PSG1218) V22.5.9.163 devices allows remote authenticated users to execute any command via shell metacharacters in the cgi-bin/luci autoUpTime parameter.