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.

Application Security

11/15/2017
07:30 AM
Connect Directly
Twitter
LinkedIn
RSS
E-Mail
50%
50%

Microsoft Uses Neural Networks to Make Fuzz Tests Smarter

Neural fuzzing can help uncover bugs in software better than traditional tools, company says.

Microsoft has developed a new technique to test software for security flaws that uses deep neural networks and machine learning techniques to improve upon current testing approaches.

Early experiments with the new "neural fuzzing" method show that it can help organizations uncover bugs in software better than traditional fuzzing tests, according to Microsoft.

Fuzzing is an approach where security testers try to uncover commonly exploitable flaws in applications by targeting the software with deliberately malformed data—or inputs—to see if it will crash so they can investigate and fix the cause.

The effectiveness of these tests depends to a large extent on how well the malicious inputs are crafted. Generally, the more input you find to trigger a crash, the more application vulnerabilities you are likely going to be able to identify and close.

Security testers can use a few different methods to generate the malicious or malformed input.

Microsoft's approach improves on one method that uses data from previous fuzz tests as feedback for creating new mutations or tests. The approach involves a "learning technique that uses neural networks to learn patterns in the input files from past fuzzing explorations to guide future fuzzing explorations," according to Microsoft.

"The neural models learn a function to predict good (and bad) locations in input files to perform fuzzing mutations based on the past mutations and corresponding code coverage information," the company said.

Neural networks are computing systems loosely modeled on the human brain that can autonomously learn from observed data. Many modern applications such as face and voice recognition and weather prediction use such networks.

Microsoft has implemented the new technique in American Fuzzy Lop (AFL), an open-source fuzzer that uses observed behavior from previous fuzzing executions to guide future tests. Researchers from the company tested the method on four target programs using parsers for the ELF, XML, PNG and PDF file formats.

The results were "very encouraging," Microsoft Development Lead William Blum said in a blog Monday. "We saw significant improvements over traditional AFL in terms of code coverage, unique code paths and crashes for the four input formats, " he said.

For instance, for the ELF parser, the neural AFL reported more than 20 crashes compared to zero with the traditional AFL fuzzer. Similarly, the neural AFL found 38% more crashes than traditional AFL for text-based file formats such as XML.

"This is astonishing given that neural AFL was trained on AFL itself," Blum said. The only area where the neural AFL did not perform as well was with PDF format, likely because of the large size of the files.

"AFL is essentially a mutational fuzzer that uses feedback from the target software to determine how the test cases are mutated," says Jonathan Knudsen, Security Strategist at Synopsys.  "Microsoft has modified the feedback mechanism with a neural network."

The challenge with any fuzzing lies in finding the finite set of malformed inputs that are most likely to trigger bugs, Knudsen says. "Microsoft has modified how AFL chooses its inputs in a way that gave them better code coverage and more bugs for a couple of applications."

Moreno Carullo, co-founder and chief technical officer of Nozomi Networks says Microsoft has broken new ground with this technique. "It is absolutely a new [and] innovative approach," Carullo says.

"Neural fuzzing increases the speed of fuzzing as a test method and also finds more issues that cause a crash," he notes. The automation behind the approach can drastically reduce the time organizations require to test their software for security vulnerabilities. "Without this, it would take a team of heuristics experts a lot more time to discover the issues."

According to Blum, the capability that Microsoft has demonstrated only scratches the surface of what can be achieved using neural networks in fuzzing. "Right now, our model only learns fuzzing locations, but we could also use it to learn other fuzzing parameters such as the type of mutation or strategy to apply," he said.

Related content:

Join Dark Reading LIVE for two days of practical cyber defense discussions. Learn from the industry’s most knowledgeable IT security experts. Check out the INsecurity agenda here.

Jai Vijayan is a seasoned technology reporter with over 20 years of experience in IT trade journalism. He was most recently a Senior Editor at Computerworld, where he covered information security and data privacy issues for the publication. Over the course of his 20-year ... View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
7 Tips for Infosec Pros Considering A Lateral Career Move
Kelly Sheridan, Staff Editor, Dark Reading,  1/21/2020
For Mismanaged SOCs, The Price Is Not Right
Kelly Sheridan, Staff Editor, Dark Reading,  1/22/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Current Issue
IT 2020: A Look Ahead
Are you ready for the critical changes that will occur in 2020? We've compiled editor insights from the best of our network (Dark Reading, Data Center Knowledge, InformationWeek, ITPro Today and Network Computing) to deliver to you a look at the trends, technologies, and threats that are emerging in the coming year. Download it today!
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2015-3154
PUBLISHED: 2020-01-27
CRLF injection vulnerability in Zend\Mail (Zend_Mail) in Zend Framework before 1.12.12, 2.x before 2.3.8, and 2.4.x before 2.4.1 allows remote attackers to inject arbitrary HTTP headers and conduct HTTP response splitting attacks via CRLF sequences in the header of an email.
CVE-2019-17190
PUBLISHED: 2020-01-27
A Local Privilege Escalation issue was discovered in Avast Secure Browser 76.0.1659.101. The vulnerability is due to an insecure ACL set by the AvastBrowserUpdate.exe (which is running as NT AUTHORITY\SYSTEM) when AvastSecureBrowser.exe checks for new updates. When the update check is triggered, the...
CVE-2014-8161
PUBLISHED: 2020-01-27
PostgreSQL before 9.0.19, 9.1.x before 9.1.15, 9.2.x before 9.2.10, 9.3.x before 9.3.6, and 9.4.x before 9.4.1 allows remote authenticated users to obtain sensitive column values by triggering constraint violation and then reading the error message.
CVE-2014-9481
PUBLISHED: 2020-01-27
The Scribunto extension for MediaWiki allows remote attackers to obtain the rollback token and possibly other sensitive information via a crafted module, related to unstripping special page HTML.
CVE-2015-0241
PUBLISHED: 2020-01-27
The to_char function in PostgreSQL before 9.0.19, 9.1.x before 9.1.15, 9.2.x before 9.2.10, 9.3.x before 9.3.6, and 9.4.x before 9.4.1 allows remote authenticated users to cause a denial of service (crash) or possibly execute arbitrary code via a (1) large number of digits when processing a numeric ...