Think of LiDAR and first thing that comes to mind is a light-based system that detects obstacles to help vehicles safely navigate roads around obstacles and through adverse conditions. But to Purdue University researchers, LiDAR—which they term as LIDAR—does not stand for light imaging, detection and ranging.
Instead, Purdue’s LIDAR is an AI-based detection system that alerts organizations to cyberattacks and 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, an assistant professor of electrical and computer engineering in Purdue’s College of Engineering, in an article on the university’s website. “Our system is robust and able to adapt to different environments through lifelong learning.”
El Gamal created the technology with Arif Ghafoor, a professor in electrical and computer engineering, and Ali Elghariani, a graduate of electrical and computer engineering.
Purdue University designed LIDAR for computer systems and networks, including wireless networks. The system works with preprocessing components that are designed to be resilient to adversarial attacks and a cross-layer feature extraction mechanism for wireless networks.
LIDAR comprises three main parts: supervised machine learning, unsupervised machine learning and rule-based learning.
The supervised machine-learning component uses an algorithm to compare abnormalities detected in the system to known attack templates. The unsupervised component uses an algorithm to detect any anomalies in the overall system being monitored.
Purdue’s LIDAR system also uses a curiosity-driven honeypot, which lures attackers but does not let them infiltrate the system.