acm-header
Sign In

Communications of the ACM

ACM TechNews

­sing Neural Nets to Snag Malware Before It Strikes


View as: Print Mobile App Share:
The problem with most antivirus/antimalware software is that it often cant detect malicious behavior until damage has been done.

Abdullah Muzahid, an assistant professor of computer science at the University of Texas at San Antonio, has received a $450,000 National Science Foundation grant to develop an artificial intelligence system that can detect software bugs and security attac

Credit: Government Computer News

University of Texas at San Antonio professor Abdullah Muzahid has received a $450,000 grant from the U.S. National Science Foundation to support his work in developing NFrame, an artificial intelligence system that can detect software bugs and security attacks in computer systems before they deploy.

Muzahid says the goal of the project is to create an accurate, adaptive, and fast self-policing computer system.

The NFrame hardware-based artificial neural network is modeled after human brain activity and is designed to recognize system behaviors and make decisions based on those recognitions.

When a program runs for the first time, Muzahid says NFrame learns how it operates at the machine level. NFrame then will monitor activity for signs of suspicious behavior.

"NFrame can not only tell you why something has gone wrong, but because of how it learns, it can also predict when something is about to go wrong in its system," Muzahid says.

From Government Computer News
View Full Article

 

Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account