针对自动驾驶模型的比特翻转故障，提出时空感知定位方法。
Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)
- 通过渐进式度量引导搜索，定位影响驾驶行为的关键权重比特
- 发现29.56倍于基线的危险故障点，提升安全评估效率
- 适合自动驾驶系统安全验证与硬件抗干扰设计人员
现代高级驾驶辅助系统（ADAS）依赖深度神经网络（DNN）进行感知与规划。由于DNN参数在推理过程中驻留在DRAM中，宇宙射线或低电压操作引发的比特翻转可能破坏计算结果，扭曲驾驶决策，导致真实事故。本文提出一种时空感知故障注入框架（STAFI），高效定位DNN中关键故障位置。空间上，采用渐进式度量引导比特搜索（PMBS）算法，快速识别导致驾驶行为最大偏差（如误加速或误转向）的关键权重比特；时间上，设计关键故障触发时间识别（CFTI）机制，结合实时系统上下文与环境状态，选择最优故障时机以最大化安全影响。在量产级ADAS的DNN上实验表明，STAFI发现的危险故障点比最强基线多29.56倍。
原文摘要 · Abstract (English)
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 faults than the strongest baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。