A Unioned Graph Neural Network Based Hardware Trojan Node Detection

The globalization of the integrated circuit (IC) industry has raised concerns about hardware Trojans (HT), and there is an urgent need for efficient HT-detection methods gate-level netlists. In this work, we propose approach to detect Trojan-nodes at gate level, based on graph learning. proposed method does not require any golden model can be easily into circuits design flow. addition, further a unioned GNN network combine information from input side, output neighbor side directed generate representative node embeddings. experimental results show that it could achieve 93.4% in recall, 91.4% F-measure, 90.7% precision average across different designs, which outperforms state-of-the-art HT detection methods.