[2604.03753] Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems

Computer Science > Cryptography and Security arXiv:2604.03753 (cs) [Submitted on 4 Apr 2026] Title:Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems Authors:Taibiao Zhao, Xiang Zhang, Mingxuan Sun, Ruyi Ding, Xugui Zhou View a PDF of the paper titled Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems, by Taibiao Zhao and 4 other authors View PDF HTML (experimental) Abstract:Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips caused by cosmic radiation or low-voltage operation may corrupt DNN computations, distort driving decisions, and lead to real-world incidents. This paper presents a SpatioTemporal-Aware Fault Injection (STAFI) framework to locate critical fault sites in DNNs for ADAS efficiently. Spatially, we propose a Progressive Metric-guided Bit Search (PMBS) that efficiently identifies critical network weight bits whose corruption causes the largest deviations in driving behavior (e.g., unintended acceleration or steering). Furthermore, we develop a Critical Fault Time Identification (CFTI) mechanism that determines when to trigger these faults, taking into account the context of real-time systems and environmental states, to maximize the safety impact. Experiments on DNNs for a production ADAS demonstrate that STAFI uncovers 29.56x more hazard-inducing critical fa...