Multi-criteria Hardware Trojan Detection: A Reinforcement Learning Approach
This addresses security vulnerabilities in hardware design for chip manufacturers and security engineers, but it appears incremental as it extends existing single-criterion methods to multi-criteria.
The paper tackles the problem of detecting Hardware Trojans (HTs) in digital integrated circuits by proposing a multi-criteria reinforcement learning tool, achieving an average of 84.2% successful detection on the ISCAS-85 benchmark.
Hardware Trojans (HTs) are undesired design or manufacturing modifications that can severely alter the security and functionality of digital integrated circuits. HTs can be inserted according to various design criteria, e.g., nets switching activity, observability, controllability, etc. However, to our knowledge, most HT detection methods are only based on a single criterion, i.e., nets switching activity. This paper proposes a multi-criteria reinforcement learning (RL) HT detection tool that features a tunable reward function for different HT detection scenarios. The tool allows for exploring existing detection strategies and can adapt new detection scenarios with minimal effort. We also propose a generic methodology for comparing HT detection methods fairly. Our preliminary results show an average of 84.2% successful HT detection in ISCAS-85 benchmark