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
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
 

Recommended Reading:

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
NSA Appoints Rob Joyce as Cyber Director
Dark Reading Staff 1/15/2021
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win an Amazon Gift Card! Click Here
Latest Comment: Hunny, I looked every where for the dorritos. 
Current Issue
2020: The Year in Security
Download this Tech Digest for a look at the biggest security stories that - so far - have shaped a very strange and stressful year.
Flash Poll
Assessing Cybersecurity Risk in Today's Enterprises
Assessing Cybersecurity Risk in Today's Enterprises
COVID-19 has created a new IT paradigm in the enterprise -- and a new level of cybersecurity risk. This report offers a look at how enterprises are assessing and managing cyber-risk under the new normal.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-8567
PUBLISHED: 2021-01-21
Kubernetes Secrets Store CSI Driver Vault Plugin prior to v0.0.6, Azure Plugin prior to v0.0.10, and GCP Plugin prior to v0.2.0 allow an attacker who can create specially-crafted SecretProviderClass objects to write to arbitrary file paths on the host filesystem, including /var/lib/kubelet/pods.
CVE-2020-8568
PUBLISHED: 2021-01-21
Kubernetes Secrets Store CSI Driver versions v0.0.15 and v0.0.16 allow an attacker who can modify a SecretProviderClassPodStatus/Status resource the ability to write content to the host filesystem and sync file contents to Kubernetes Secrets. This includes paths under var/lib/kubelet/pods that conta...
CVE-2020-8569
PUBLISHED: 2021-01-21
Kubernetes CSI snapshot-controller prior to v2.1.3 and v3.0.2 could panic when processing a VolumeSnapshot custom resource when: - The VolumeSnapshot referenced a non-existing PersistentVolumeClaim and the VolumeSnapshot did not reference any VolumeSnapshotClass. - The snapshot-controller crashes, ...
CVE-2020-8570
PUBLISHED: 2021-01-21
Kubernetes Java client libraries in version 10.0.0 and versions prior to 9.0.1 allow writes to paths outside of the current directory when copying multiple files from a remote pod which sends a maliciously crafted archive. This can potentially overwrite any files on the system of the process executi...
CVE-2020-8554
PUBLISHED: 2021-01-21
Kubernetes API server in all versions allow an attacker who is able to create a ClusterIP service and set the spec.externalIPs field, to intercept traffic to that IP address. Additionally, an attacker who is able to patch the status (which is considered a privileged operation and should not typicall...