Lune

USENIX Security2025顶会

Automated Discovery of Semantic Attacks in Multi-Robot Navigation Systems

Doguhan Yeke, Kartik Anand Pant, Muslum Ozgur Ozmen, Hyungsub Kim, James M. Goppert, Inseok Hwang, Antonio Bianchi, Z. Berkay Celik

摘要

Finding collision-free paths is crucial for autonomous multirobots (AMRs) to complete assigned missions, ranging from search operations to military tasks. To achieve this, AMRs rely on collaborative collision avoidance algorithms. Unfortunately, the robustness of these algorithms against false data injection attacks (FDIAs) remains unexplored. In this paper, we introduce Raven, a tool to identify effective and stealthy semantic attacks (e.g., herding). Effective attacks minimize positional displacement and the number of false data injections by using temporal logic and stochastic optimization techniques. Stealthy attacks remain within sensor noise ranges and maintain spatiotemporal consistency. We evaluate Raven against two state-of-the-art collision avoidance algorithms, ORCA and GLAS. Our results show that a single false data injection impacts multi-robot systems by causing position deviation or even collisions. We evaluate Raven on three testbeds-a numerical simulator, a high-fidelity simulator, and Crazyflie drones. Our results reveal five design flaws in these algorithms and underscore the importance of developing robust defenses against FDIAs. Finally, we propose countermeasures to mitigate the attacks we have uncovered.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

可以从这些问题问起

Lune 可以查阅

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • PGPatch: Policy-Guided Logic Bug Patching for Robotic Vehicles 引用了 Cyber-Physical Inconsistency Vulnerability Identification for Safety Checks in Robotic Vehicles
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

它引用的 Paper11

  1. Adversarial Sensor Attack on LiDAR-based Perception in Autonomous DrivingYulong Cao, Chaowei Xiao, Benjamin Cyr, Yimeng Zhou 等CCS 2019 · 626 次引用
  2. M2MON: Building an MMIO-based Security Reference Monitor for Unmanned VehiclesArslan Khan, Hyungsub Kim, Byoungyoung Lee, Dongyan Xu 等USENIX Security 2021 · 35 次引用
  3. Cyber-Physical Inconsistency Vulnerability Identification for Safety Checks in Robotic VehiclesHongjun Choi, Sayali Kate, Yousra Aafer, Xiangyu Zhang 等CCS 2020 · 22 次引用
  4. SWARMFLAWFINDER: Discovering and Exploiting Logic Flaws of Swarm AlgorithmsChijung Jung, Ali Ahad, Yuseok Jeon, Yonghwi KwonS&P 2022 · 16 次引用
  5. PGPatch: Policy-Guided Logic Bug Patching for Robotic VehiclesHyungsub Kim, Muslum Ozgur Ozmen, Z. Berkay Celik, Antonio Bianchi 等S&P 2022 · 15 次引用

相关 Paper

  1. Verifying Smart Contract Security against Re-entrancy Attacks through Relational Value AnalysisDivya Rathore, Kartik NagarFSE 2026
  2. RSFuzz: A Robustness-Guided Swarm Fuzzing Framework Based on Behavioral ConstraintsRuoyu Zhou, Zhiwei Zhang, Haocheng Han, Xiaodong Zhang 等ASE 2025
  3. IMUFuzzer: Resilience-based Discovery of Signal Injection Attacks on Robotic Aerial VehiclesSudharssan Mohan, Kyeongseok Yang, Zelun Kong, Yonghwi Kwon 等ASE 2025
  4. Propaganda AI: An Analysis of Semantic Divergence in Large Language ModelsNay Myat Min, Long H. Pham, Yige Li, Jun SunICLR 2026 · 3 次引用
  5. COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic AttacksZijian Huang, Wenda Chu, Linyi Li, Chejian Xu 等AAAI 2025 · 2 次引用
黄昏的海面,两侧是细线勾勒的悬崖