The proliferation of AI technology gives rise to a variety of security threats, which significantly compromise the confidentiality and integrity of AI models and applications. Existing software-based solutions mainly target one specific attack, and require the implementation into the models, rendering them less practical. We design UniGuard, a novel unified and non-intrusive detection methodology to safeguard FPGA-based AI accelerators. The core idea of UniGuard is to harness power side-channel information generated during model inference to spot any anomaly. We employ a Time-to-Digital Converter to capture power fluctuations and train a supervised machine learning model to identify various types of threats. Evaluations demonstrate that UniGuard can achieve 94.0% attack detection accuracy, with high generalization over unknown or adaptive attacks and robustness against varied configurations (e.g., sensor frequency and location).
@article{arxiv.2311.16684,
title = {A Unified Hardware-based Threat Detector for AI Accelerators},
author = {Xiaobei Yan and Han Qiu and Tianwei Zhang},
journal= {arXiv preprint arXiv:2311.16684},
year = {2023}
}