An AI Architecture with the Capability to Classify and Explain Hardware Trojans

Abstract--Hardware trojan detection methods, based on machine learning (ML) techniques, mainly identify suspected circuits but lack the ability to explain how the decision was arrived at. An explainable methodology and architecture is introduced based on the existing hardware trojan detection features. Results are provided for explaining digital hardware trojans within a netlist using trust-hub trojan benchmarks. Hardware trojans are malware circuits that are injected within an integrated circuit (IC) during design stages, before the IC is manufactured. Once manufactured, the trojan cannot be removed nor can it be easily bypassed by software patches because it is baked into the IC chip.