Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning
This work addresses hardware security challenges for chip manufacturers by offering an incremental improvement in Trojan detection through multimodal and uncertainty-aware methods.
The paper tackled the problem of detecting hardware Trojans in chip production by proposing a multimodal deep learning approach that uses generative adversarial networks to amplify data in graph and tabular modalities, achieving improved detection accuracy and enabling uncertainty quantification for risk-aware decisions.
The risk of hardware Trojans being inserted at various stages of chip production has increased in a zero-trust fabless era. To counter this, various machine learning solutions have been developed for the detection of hardware Trojans. While most of the focus has been on either a statistical or deep learning approach, the limited number of Trojan-infected benchmarks affects the detection accuracy and restricts the possibility of detecting zero-day Trojans. To close the gap, we first employ generative adversarial networks to amplify our data in two alternative representation modalities, a graph and a tabular, ensuring that the dataset is distributed in a representative manner. Further, we propose a multimodal deep learning approach to detect hardware Trojans and evaluate the results from both early fusion and late fusion strategies. We also estimate the uncertainty quantification metrics of each prediction for risk-aware decision-making. The outcomes not only confirms the efficacy of our proposed hardware Trojan detection method but also opens a new door for future studies employing multimodality and uncertainty quantification to address other hardware security challenges.