Attacks/Breaches
3/24/2017
11:30 AM
Connect Directly
Twitter
LinkedIn
RSS
E-Mail
100%
0%

Sandia Testing New Intrusion Detection Tool That Mimics Human Brain

Neuromorphic Data Microscope can spot malicious patterns in network traffic 100 times faster than current tool, lab claims.

A project that started off as a medical study into cerebral palsy in children has yielded a technology that its creators say could help organizations detect cyberthreats 100 times faster than current products.

The technology was developed by Boston-area startup Lewis Rhodes Labs (LRL) and fine-tuned with the active participation of researchers from Sandia National Laboratories and is called the Neuromorphic Data Microscope.

The technology—currently implemented in the form of a PCIe based processing card—can be used to inspect large volumes of streaming data to find patterns that match known bad behavior faster and more cost-effectively than presently possible, according to the two organizations.

Typical intrusion detection systems sequentially compare relatively small chunks of network data against a library of known malicious patterns to spot threats. The Neuromorphic Data Microscopic does the same pattern matching in a much faster and more parallel manner that mimics the way the human brain processes streaming data.

“One way of thinking about it is when you try matching patterns on a computer, it is a more serial process,” says David Follett, CEO and co-founder of LRL. “The brain is massively parallel.”

It streams data – such as the things within an individual’s range of vision – past stored memory in a very efficient way to help the individual identify people, places, or things that are familiar. 

The Neuromorphic Data Microscope takes the same approach to inspecting massive volumes of streaming network data and finding patterns that suggest malicious behavior. It accomplishes in a single processor card the same level of parallelism that would take multiple racks of traditional cybersecurity systems working in parallel to deliver.

In its current form, the technology accelerates complex pattern matching by a factor of over 100 while using 1,000 times less power than conventional cybersecurity systems, Follett says. LRL will soon implement an ASIC version of the data microscope that will be capable of delivering a 10,000 times performance gain over current intrusion detection tools, he says.

Such capabilities will enable far more complex pattern matching and will allow organizations to spot attacks that are easy to miss currently, says Sandia computer systems expert John Naegle.

“We want to run much more complicated and sophisticated rules against our data to detect malicious types of patterns,” says Naegle. Because of the enormous computing resources it would take to run some of these rules, however, Sandia has had to make conscious decisions about what it can and cannot do with its available computing resources.

“This gives us the opportunity to drastically change the way we do cybersecurity,” Naegle says. “Right now tools are expensive, cumbersome, and very CPU-constrained” to allow for the kind of complex pattern matching Sandia has wanted to do. “This technology gives us an entirely different way to look at the problem and an entirely different way to look for suspicious traffic.”

Naegle describes the data microscope as similar in concept to the Snort open-source intrusion detection tool used by many organizations, including Sandia.

Organizations are under increasing pressure to find better and quicker ways of detecting malicious behavior on their networks. Cybercriminals often are able to easily circumvent many pattern-matching, signature-based intrusion detection systems by making relatively small changes to their malware. So capabilities like those claimed by Sandia and LRL could make a bigger difference.

The idea for the data microscope evolved from a mathematical model that LRL researchers developed for comparing the brains of children suffering from cerebral palsy with brains that do not have the disorder. In using the model, the researchers realized they had developed a way of doing computing that mimicked the manner in which a human brain processes information, a description of the technology on LRL’s website noted.

Sandia is using the Neuromorphic Data Microscope for cybersecurity purposes. But it can be used in a wide range of other applications involving the use of massive volumes of streaming data, Follett says. Examples include applications such as image and video processing, consumer data analysis, fraud identification, and financial trading.

Related stories:

 

 

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
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
Security Operations and IT Operations: Finding the Path to Collaboration
A wide gulf has emerged between SOC and NOC teams that's keeping both of them from assuring the confidentiality, integrity, and availability of IT systems. Here's how experts think it should be bridged.
Flash Poll
New Best Practices for Secure App Development
New Best Practices for Secure App Development
The transition from DevOps to SecDevOps is combining with the move toward cloud computing to create new challenges - and new opportunities - for the information security team. Download this report, to learn about the new best practices for secure application development.
Slideshows
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2017-0290
Published: 2017-05-09
NScript in mpengine in Microsoft Malware Protection Engine with Engine Version before 1.1.13704.0, as used in Windows Defender and other products, allows remote attackers to execute arbitrary code or cause a denial of service (type confusion and application crash) via crafted JavaScript code within ...

CVE-2016-10369
Published: 2017-05-08
unixsocket.c in lxterminal through 0.3.0 insecurely uses /tmp for a socket file, allowing a local user to cause a denial of service (preventing terminal launch), or possibly have other impact (bypassing terminal access control).

CVE-2016-8202
Published: 2017-05-08
A privilege escalation vulnerability in Brocade Fibre Channel SAN products running Brocade Fabric OS (FOS) releases earlier than v7.4.1d and v8.0.1b could allow an authenticated attacker to elevate the privileges of user accounts accessing the system via command line interface. With affected version...

CVE-2016-8209
Published: 2017-05-08
Improper checks for unusual or exceptional conditions in Brocade NetIron 05.8.00 and later releases up to and including 06.1.00, when the Management Module is continuously scanned on port 22, may allow attackers to cause a denial of service (crash and reload) of the management module.

CVE-2017-0890
Published: 2017-05-08
Nextcloud Server before 11.0.3 is vulnerable to an inadequate escaping leading to a XSS vulnerability in the search module. To be exploitable a user has to write or paste malicious content into the search dialogue.

Dark Reading Radio
Archived Dark Reading Radio
In past years, security researchers have discovered ways to hack cars, medical devices, automated teller machines, and many other targets. Dark Reading Executive Editor Kelly Jackson Higgins hosts researcher Samy Kamkar and Levi Gundert, vice president of threat intelligence at Recorded Future, to discuss some of 2016's most unusual and creative hacks by white hats, and what these new vulnerabilities might mean for the coming year.