Hardware Trojan Insertion Using Reinforcement Learning
This work addresses the need for robust Hardware Trojan detection in digital circuits, though it is incremental as it applies existing RL methods to a specific domain.
The paper tackles the problem of automating Hardware Trojan insertion to improve detection methods by using Reinforcement Learning to find optimal circuit locations for hidden Trojans, achieving 100% input coverage in two benchmark circuits with minimal footprint and rare activation.
This paper utilizes Reinforcement Learning (RL) as a means to automate the Hardware Trojan (HT) insertion process to eliminate the inherent human biases that limit the development of robust HT detection methods. An RL agent explores the design space and finds circuit locations that are best for keeping inserted HTs hidden. To achieve this, a digital circuit is converted to an environment in which an RL agent inserts HTs such that the cumulative reward is maximized. Our toolset can insert combinational HTs into the ISCAS-85 benchmark suite with variations in HT size and triggering conditions. Experimental results show that the toolset achieves high input coverage rates (100\% in two benchmark circuits) that confirms its effectiveness. Also, the inserted HTs have shown a minimal footprint and rare activation probability.