Saturday, October 21, 2017

UTSA professor wins $450,000 NSF grant to develop artificial intelligence that can detect computer system faults

UTSA professor wins $450,000 NSF grant to develop artificial intelligence that can detect computer system faults

Abdullah Muzahid’s NFrame network would learn, monitor and detect “bad behavior” in computer programs

Abdullah Muzahid, assistant professor of computer science at The University of Texas at San Antonio (UTSA), has received a $450,000 National Science Foundation (NSF) Faculty Early Career Development award to develop a hardware-based artificial intelligence system that can detect costly software bugs and security attacks in computer systems.

Businesses spend millions on cybersecurity and bug fixes each year. A 2016 report by the International Data Corporation estimated that more than $73.7 billion is spent worldwide in security-related hardware, software and service expenses. Muzahid and his collaborators hope to significantly decrease those expenditures by developing a new system that can catch bugs and attacks before they cause harm.

Muzahid and his team of undergraduate and graduate students will over the next five years develop an artificial neural network (ANN) that can detect, avoid and expose the root causes of system faults, bugs and security attacks. ANNs are computer systems modeled after the human brain and nervous system that are designed to recognize system behaviors and make decisions based on those recognitions.

“Our goal with our network, which we are calling NFrame, is to create a self-policing computer system that is accurate, adaptive and fast,” said Muzahid, whose top-tier research focuses on improving the programmability of computer architecture by providing various support in the hardware. “Not only is our approach the first to use neural network hardware in this way, but its processes will give new insights into the causes and manifestations of bugs, security flaws and computer system faults.”

“NFrame” monitor computer code, data and program instructions to learn the “acceptable” or normal behaviors of the various software programs running on its system. Behaviors that deviate from those defined parameters would be identified as bugs or attacks.

Muzahid says that NFrame could, for example, alert its users to why a specific software keeps crashing. It could pinpoint security flaws in programs and report whether the program has been compromised as a result. NFrame would also potentially be able to flag and prevent a program from sending information to any unauthorized third-parties that may be attempting to break into the system at any time.

“NFrame could not only tell you why something has gone wrong, but because of how it is designed to learn it could also predict when something is about to go wrong,” said Muzahid. “The network should also be able to report to users what is wrong, how it is wrong, where it is wrong, why it is wrong and whether something will be wrong in the future. This is possible because of how we are designing NFrame to run off specialized hardware.” 

The majority of ANNs are built in software. NFrame will be built directly into the hardware running its computer systems. Muzahid says that this would allow the ANN to adapt and evolve with its host-system at incredible speeds.

“Hardware-based ANNs are able to process information and make decisions at more than 100 times the speed of software-based networks,” said Muzahid, who has completed a prototype of NFrame but plans to refine it and develop the hardware further in the coming years.

Additionally, Muzahid and his team plan to create courses for UTSA and local high school students which focus on the future of computing and machine learning.

“In an ideal world, we will one day be able to have adaptive artificial neural networks like NFrame on every computer system to help it protect itself from software bugs and other risks that can make it vulnerable to attack or intrusion,” Muzahid said. "In the meantime, we want also to educate future programmers about the best approaches to cybersecurity."

Muzahid is the seventh faculty member in the Department of Computer Science, housed in the UTSA College of Sciences, to receive the distinguished NSF Career Award, which is awarded to the most promising junior faculty members in the nation in order to assist them in developing their careers as teachers and scholars.

“Abdullah Muzahid’s novel approach to detecting and reacting to bugs and security attacks in computer systems using an artificial neural network is closely aligned with UTSA’s academic and research focus to helping solve the pressing issues that are significant to the industry today,” said Rajendra Boppana, professor and department chair. “It will be exciting to see how NFrame develops in the coming years.”

UTSA is ranked among the top 400 universities in the world and among the top 100 in the nation, according to Times Higher Education.

- Jesus Chavez


Learn more about the UTSA College of Sciences and the Department of Computer Science.

Learn more about Cybersecurity at UTSA.

Connect with UTSA online at Facebook, Twitter, Vimeo and Instagram.




Events