DETERRENT: Detecting Trojans using Reinforcement Learning
TimeWednesday, July 13th2:37pm - 3pm PDT
Location3006, Level 3
Event Type
Research Manuscript
Hardware Security: Attack and Defense
DescriptionInsertion of hardware Trojans in integrated circuits is a pernicious threat. Since Trojans are activated under rare trigger conditions, detecting them using random logic simulations is infeasible. In this work, we design a reinforcement learning (RL) agent that circumvents the exponential search space and returns a minimal set of patterns that is most likely to detect Trojans. Experimental results on a variety of benchmarks demonstrate the efficacy and scalability of our RL agent, which obtains a significant reduction in the number of test patterns required while maintaining the same coverage compared to the state-of-the-art techniques.