mlsanityData to 14 Oct 2026

Adversarial Attacks On Multi-Agent Communication

arXiv 2101.06560 ↗First posted 17 Jan 2021cs.LG cs.CR cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks and increase computation efficiency. However, shared information can be modified to execute adversarial attacks on deep learning models that are widely employed in modern systems. Thus, we aim to study the robustness of such systems and focus on exploring adversarial attacks in a novel multi-agent setting where communication is done through sharing learned intermediate representations of neural networks. We observe that an indistinguishable adversarial message can severely degrade performance, but becomes weaker as the number of benign agents increases. Furthermore, we show that black-box transfer attacks are more difficult in this setting when compared to directly perturbing the inputs, as it is necessary to align the distribution of learned representations with domain adaptation. Our work studies robustness at the neural network level to contribute an additional layer of fault tolerance to modern security protocols for more secure multi-agent systems.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 42 of its 63 references that are in the map. First posted on arXiv 17 Jan 2021.

Builds on

42 of 63 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  10. 2018Group Normalizationcited by 1,524
  11. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  12. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
30 more
  1. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  3. 2018Robustness May Be at Odds with Accuracycited by 880
  4. 2019Towards Federated Learning at Scale: System Designcited by 832
  5. 2017Focal Loss for Dense Object Detectioncited by 752
  6. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  10. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  12. 2017Adversarial Attacks on Neural Network Policiescited by 320
  13. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  14. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  15. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 264
  16. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 152
  17. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 140
  18. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  19. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  20. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  21. 2016Crafting Adversarial Input Sequences for Recurrent Neural Networkscited by 103
  22. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  23. 2018Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examplescited by 94
  24. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
  25. 2020Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalizationcited by 73
  26. 2018Interpretable Adversarial Perturbation in Input Embedding Space for Textcited by 67
  27. 2019Black-box Adversarial Attacks on Video Recognition Modelscited by 58
  28. 2018Sparse Adversarial Perturbations for Videoscited by 57
  29. 2018Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attackscited by 46
  30. 2018Geometry-Aware Recurrent Neural Networks for Active Visual Recognitioncited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 12; 2024: 6; 2025: 10; 2026: 10.

49 papers.

Sort:

By area:

  1. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  2. 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
  3. 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
  4. 2022Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communicationcited by 47
  5. 2025STAMP: Scalable Task And Model-agnostic Collaborative Perceptioncited by 44
  6. 2023Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perceptioncited by 38
  7. 2023Among Us: Adversarially Robust Collaborative Perception by Consensuscited by 37
  8. 2022V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perceptioncited by 28
  9. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  10. 2021Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learningcited by 18
  11. 2023S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Realitycited by 18
  12. 2022Robust Trajectory Prediction against Adversarial Attackscited by 17
37 more
  1. 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 17
  2. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  3. 2023Vehicle-to-Everything Cooperative Perception for Autonomous Drivingcited by 15
  4. 2024A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challengescited by 13
  5. 2024CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perceptioncited by 13
  6. 2024V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditionscited by 12
  7. 2023On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasurescited by 11
  8. 2022Collaborative Perception for Autonomous Driving: Current Status and Future Trendcited by 10
  9. 2023Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulationcited by 10
  10. 2025GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detectioncited by 8
  11. 2022Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systemscited by 7
  12. 2023Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RLcited by 7
  13. 2024RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modelingcited by 6
  14. 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learningcited by 6
  15. 2023Robust Communicative Multi-Agent Reinforcement Learning with Active Defensecited by 5
  16. 2025UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learningcited by 5
  17. 2025CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detectioncited by 4
  18. 2022AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learningcited by 3
  19. 2023SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learningcited by 3
  20. 2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
  21. 2025CP-FREEZER: Latency Attacks against Vehicular Cooperative Perceptioncited by 3
  22. 2026Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perceptioncited by 3
  23. 2026AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operationscited by 2
  24. 2021Adversarial Attacks in Cooperative AIcited by 1
  25. 2022Ad Hoc Teamwork in the Presence of Adversariescited by 1
  26. 2024Collaborative Perception in Multi-Robot Systems: Case Studies in Household Cleaning and Warehouse Operationscited by 1
  27. 2025CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systemscited by 1
  28. 2026Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learningcited by 1
  29. 2026Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learningcited by 1
  30. 2026PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learningcited by 1
  31. 2025Robustifying 3D Perception via Least-Squares Graphs for Multi-Agent Object Trackingcited by 0
  32. 2025SAJA: A State-Action Joint Attack Framework on Multi-Agent Deep Reinforcement Learningcited by 0
  33. 2026All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inferencecited by 0
  34. 2026HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perceptioncited by 0
  35. 2026Finding the Weakest Link: Adversarial Attack against Multi-Agent Communicationscited by 0
  36. 2026Adversarial Trust Poisoning in Vehicular Collaborative Perceptioncited by 0
  37. 2026Investigating Adversarial Robustness of Heterogeneous Cooperative Perceptioncited by 0