Attack Detection using Time Series Foundation Models
Researchers have developed a novel method for detecting attacks in cyber-physical systems using a time-series foundation model called TimesFM. This approach does not require prior knowledge of the system's model or structure. The TimesFM-based detector demonstrated comparable or superior performance to existing methods in detecting both replay and stealthy attacks, as shown in simulations on the IEEE 14-bus power system. AI
IMPACT This research could lead to more robust defenses against sophisticated cyberattacks in critical infrastructure.