Rare Node Targeted Trojan Detection Using Test Pattern Optimization With NSGA-II and ACO

The detection of hardware Trojans (HTs) is critical for ensuring the security and reliability of integrated circuits (ICs), as these malicious modifications can compromise system confidentiality and functionality. Traditional detection methods, such as Automatic Test Pattern Generation (ATPG), often struggle to identify covert and small combinational Trojans, particularly when inserted in rare nodes. Rare nodes are ideal targets for Trojan insertion, as they can evade conventional de-tection mechanisms. This work introduces a novel multi-objective optimization framework that targets these rare nodes to enhance Trojan detection. By integrating Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and Ant Colony Optimization (ACO), the proposed methodology optimizes test pattern generation specifically for these vulnerable points. Trojans are deliberately inserted into the rare nodes of combinational benchmark circuits, and NSGA-II generates optimized test patterns, which are then refined by ACO to improve detection effectiveness while minimizing the total number of test patterns needed.