CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems
Not on the map. Why?
Abstract (arXiv)
Collaborative Perception (CP) has been shown to be a promising technique for multi-agent autonomous driving and multi-agent robotic systems, where multiple agents share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, an ego agent needs to receive messages from its collaborators, which makes it vulnerable to attacks from malicious agents. To address this critical issue, we propose a unified, probability-agnostic, and adaptive framework, namely, CP-uniGuard, which is a tailored defense mechanism for CP deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is to enable CP to reach a consensus rather than a conflict against an ego agent's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method to effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we define collaborative consistency loss (CCLoss) for object detection task and bird's eye view (BEV) segmentation task to capture the discrepancy between an ego agent and its collaborators, which is used as a verification criterion for consensus. In addition, we propose online adaptive threshold via dual sliding windows to dynamically adjust the threshold for consensus verification and ensure the reliability of the systems in dynamic environments. Finally, we conduct extensive experiments and demonstrate the effectiveness of our framework. Code is available at https://github.com/CP-Security/CP-uniGuard.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 28 Jun 2025.
Builds on
34 of 49 references.
References · 34
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
- 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 273
- 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
- 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 210
- 2022V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Drivingcited by 157
- 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 149
- 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
- 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
22 more
- 2019IoU Loss for 2D/3D Object Detectioncited by 128
- 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
- 2024An Extensible Framework for Open Heterogeneous Collaborative Perceptioncited by 87
- 2022Latency-Aware Collaborative Perceptioncited by 86
- 2018Adversarial Examples: Opportunities and Challengescited by 63
- 2021Adversarial Attacks On Multi-Agent Communicationcited by 49
- 2024AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learningcited by 40
- 2023Among Us: Adversarially Robust Collaborative Perception by Consensuscited by 37
- 2024Collaborative Perception for Connected and Autonomous Driving: Challenges, Possible Solutions and Opportunitiescited by 32
- 2021Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehiclescited by 26
- 2021Fooling LiDAR Perception via Adversarial Trajectory Perturbationcited by 25
- 2023Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Drivingcited by 25
- 2024AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Mergingcited by 22
- 2023Adaptive Communications in Collaborative Perception with Domain Alignment for Autonomous Drivingcited by 19
- 2024PACP: Priority-Aware Collaborative Perception for Connected and Autonomous Vehiclescited by 17
- 2024Prioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analyticscited by 17
- 2024Directed-CP: Directed Collaborative Perception for Connected and Autonomous Vehicles via Proactive Attentioncited by 14
- 2024CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perceptioncited by 13
- 2023On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasurescited by 11
- 2024What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perceptioncited by 11
- 2023Malicious Agent Detection for Robust Multi-Agent Collaborative Perceptioncited by 8
- 2025CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perceptioncited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.