With cybersecurity attacks on the rise, the FBI has warned possible targets such as big cities that this trend will most likely continue, according to a Purdue press release.
To alert organizations about cyberattacks, a new system has been developed by researchers from Purdue. This system is named LIDAR, which stands for lifelong, intelligent, diverse, agile and robust.
“The name for this architecture for network security really defines its significant attributes,” said Aly El Gamal, a professor of electrical and computer engineering, according to the release. “Our system is robust and able to adapt to different environments through lifelong learning.”
The project's two other researchers were Arif Ghafoor, an ECE professor, and Ali Elghariani, an ECE alumnus.
According to the release, LIDAR can work with computer systems and networks. A cross-layer feature extraction mechanism is added when working with a wireless network. It is composed of three parts, including supervised machine learning, unsupervised machine learning and rule-based learning. The system also includes a honeypot feature that lures attackers in but does not let them penetrate the system.
“One of the fascinating things about LIDAR is that the rule-based learning component really serves as the brain for the operation,” El Gamal said in the release. “That component takes the information from the other two parts and decides the validity of a potential attack and necessary steps to move forward.”
Two algorithms are used, according to the release. One works with the supervised machine learning and analyzes abnormalities against known attack templates. The second works with the unsupervised machine learning and monitors the entire system to check for inconsistencies.
Currently, the researchers are looking for a way to patent LIDAR with Purdue Research Foundation's Office of Technology Commercialization, according to the release.