为感知类神经网络提供运行时安全监控，防故障于未然
Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey
- 不修改模型，在推理时并行检测输入、中间特征和输出异常
- 分类三类监控方法，覆盖分布外输入、对抗攻击等安全风险
- 适合自动驾驶、机器人等高危场景的可靠性验证
深度神经网络（DNN）广泛应用于自动驾驶、机器人等安全关键型感知系统，但依然面临泛化误差、分布外（OOD）输入及对抗攻击等安全挑战，可能导致严重故障。本文综述了运行时安全监控技术，该类方法在推理阶段与DNN并行运行，无需修改模型即可检测上述安全问题。我们将其分为三类：输入监控、内部表征监控和输出监控。系统分析各类别最新进展，总结优缺点，并映射到对应的安全风险。此外，还指出当前开放挑战与未来研究方向。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) are widely used in perception systems for safety-critical applications, such as autonomous driving and robotics. However, DNNs remain vulnerable to various safety concerns, including generalization errors, out-of-distribution (OOD) inputs, and adversarial attacks, which can lead to hazardous failures. This survey provides a comprehensive overview of runtime safety monitoring approaches, which operate in parallel to DNNs during inference to detect these safety concerns without modifying the DNN itself. We categorize existing methods into three main groups: Monitoring inputs, internal representations, and outputs. We analyze the state-of-the-art for each category, identify strengths and limitations, and map methods to the safety concerns they address. In addition, we highlight open challenges and future research directions.
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。