面向感知的深度神经网络运行时安全监控：综述
Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey
AI总结：
本文综述了深度神经网络感知系统的运行时安全监控方法，将其分为监控输入、内部表示和输出三类，分析各自优劣并指出未来研究方向。
摘要：
深度神经网络（DNNs）广泛应用于安全关键型应用的感知系统中，例如自动驾驶和机器人技术。然而，DNNs 仍然容易受到各种安全问题的影响，包括泛化误差、分布外（OOD）输入和对抗性攻击，这些都可能导致危险的故障。本综述对运行时安全监控方法进行了全面概述，这些方法在推理过程中与 DNNs 并行运行，以检测这些安全问题，而无需修改 DNN 本身。我们将现有方法分为三大类：监控输入、内部表示和输出。我们分析了每个类别的最新技术，识别了其优势和局限性，并将方法映射到它们所解决的安全问题。此外，我们还强调了开放性挑战和未来的研究方向。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
