用机器学习模拟限时攻击者，测试多机器人巡逻系统的漏洞。
Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study
- 构建能观察巡逻行为的智能攻击模型，限时突破安全区域。
- 相比基线方法，攻击成功率显著提升，测试更严格。
- 适合评估和优化去中心化巡逻策略的安全性。
模拟物理自主系统的敌对攻击可有效检验其抗攻击能力，并为漏洞感知设计提供依据。本文以多机器人巡逻为场景，提出一种基于机器学习的对抗模型，该模型通过观察机器人巡逻行为，在有限时间内尝试未被察觉地进入安全区域。该模型能够评估巡逻系统面对现实潜在攻击者的鲁棒性，为未来巡逻策略设计提供洞见。实验表明，该模型优于现有基线方法，提供了更严格的测试标准，并对其在多种主流去中心化多机器人巡逻策略上的表现进行了评估。
原文摘要 · Abstract (English)
Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies.
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。