Researchers develop algorithm to detect cyber attacks
In an effort to combat cyber attacks, North Carolina State University researchers have developed a software algorithm to detect and isolate cyber-attacks.
Washington: In an effort to combat cyber attacks, North Carolina State University researchers have developed a software algorithm to detect and isolate cyber-attacks on networked control systems that play an important role in coordinating transportation, power and other infrastructure across the United States.
The networked control systems not only connect and coordinate activities between computers and physical devices, but also connect temperature sensors, heating systems and user controls in modern buildings. Largely used for transportation and power in the national infrastructure, the networked control systems are vulnerable to cyber-attacks.
Two costly, high-profile software called `Flame` and `Stuxnet` have been used to attack networked control systems in recent years.
The huge and complex structure of the networked control systems have provoked designers to create `distributed network control systems` (D-NCSs) to allow all the system agents to work together and coordinate their activities, allowing the systems to operate more efficiently and more safely.
The researchers have successfully developed a software algorithm to detect an individual agent in a D-NCS if it has been compromised to a cyber-attack. The algorithm then isolates the compromised agent, protecting the rest of the system and allowing it to continue functioning normally, thereby providing more resilience and security advantages to D-NCSs over systems that rely on a central computer hub.
Professor of electrical and computer engineering at NC State Dr. Mo-Yuen Chow said that the security algorithm can be incorporated directly into the code used to operate existing distributed control systems, with minor modifications and will not require a complete overhaul of existing systems.
A Ph.D. student at NC State Wente Zeng further said that the researchers are working on additional testing under various cyber-attack scenarios to optimize the algorithm`s detection rate and system performance.