mlsanityData to 14 Oct 2026

SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving

arXiv 2510.18123 ↗First posted 20 Oct 2025cs.CV cs.AI cs.CLcited by 2

On the map: End-to-end autonomous driving → Cooperative and V2X driving

also in 1 more
Abstract (arXiv)

Collaborative driving systems leverage vehicle-to-everything (V2X) communication across multiple agents to enhance driving safety and efficiency. Traditional V2X systems take raw sensor data, neural features, or perception results as communication media, which face persistent challenges, including high bandwidth demands, semantic loss, and interoperability issues. Recent advances investigate natural language as a promising medium, which can provide semantic richness, decision-level reasoning, and human-machine interoperability at significantly lower bandwidth. Despite great promise, this paradigm shift also introduces new vulnerabilities within language communication, including message loss, hallucinations, semantic manipulation, and adversarial attacks. In this work, we present the first systematic study of full-stack safety and security issues in natural-language-based collaborative driving. Specifically, we develop a comprehensive taxonomy of attack strategies, including connection disruption, relay/replay interference, content spoofing, and multi-connection forgery. To mitigate these risks, we introduce an agentic defense pipeline, which we call SafeCoop, that integrates a semantic firewall, language-perception consistency checks, and multi-source consensus, enabled by an agentic transformation function for cross-frame spatial alignment. We systematically evaluate SafeCoop in closed-loop CARLA simulation across 32 critical scenarios, achieving 69.15% driving score improvement under malicious attacks and up to 67.32% F1 score for malicious detection. This study provides guidance for advancing research on safe, secure, and trustworthy language-driven collaboration in transportation systems. Our project page is https://xiangbogaobarry.github.io/SafeCoop.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Cooperative and V2X driving, one of 9 directions in End-to-end autonomous driving. Builds on 101 of its 138 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

101 of 138 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance1 Aug
  2. 2025Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition29 Jul
  3. 2025CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning23 May
  4. 2025LangCoop: Collaborative Driving with Language18 Apr
  5. 2025V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models14 Feb
  6. 2024Towards Interactive and Learnable Cooperative Driving Automation: a Large Language Model-Driven Decision-Making Framework19 Sep
  7. 2024V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models17 Aug
  8. 2024Towards Collaborative Autonomous Driving: Simulation Platform and End-to-End System15 Apr
  9. 2022COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles4 May

Other references · 92

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  6. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
  7. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  8. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 461
  9. 2023GPT-Driver: Learning to Drive with GPTcited by 347
  10. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  11. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  12. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
38 more
  1. 2023Think before you speak: Training Language Models With Pause Tokenscited by 264
  2. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 260
  3. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  4. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  5. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  6. 2023DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Modelscited by 207
  7. 2024Let's Think Dot by Dot: Hidden Computation in Transformer Language Modelscited by 191
  8. 2019Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Cloudscited by 165
  9. 2023A Language Agent for Autonomous Drivingcited by 164
  10. 2024Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Drivingcited by 156
  11. 2020Who2com: Collaborative Perception via Learnable Handshake Communicationcited by 127
  12. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 126
  13. 2024VLP: Vision Language Planning for Autonomous Drivingcited by 126
  14. 2019Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensorscited by 110
  15. 2023ADriver-I: A General World Model for Autonomous Drivingcited by 104
  16. 2024OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Drivingcited by 93
  17. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 92
  18. 2024An Extensible Framework for Open Heterogeneous Collaborative Perceptioncited by 87
  19. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 86
  20. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  21. 2024SafeBench: A Safety Evaluation Framework for Multimodal Large Language Modelscited by 69
  22. 2020DSDNet: Deep Structured self-Driving Networkcited by 62
  23. 2022Bridging the Domain Gap for Multi-Agent Perceptioncited by 60
  24. 2024Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Drivingcited by 56
  25. 2022Model-Agnostic Multi-Agent Perception Frameworkcited by 51
  26. 2024VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Drivingcited by 51
  27. 2025STAMP: Scalable Task And Model-agnostic Collaborative Perceptioncited by 44
  28. 2024DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Drivingcited by 43
  29. 2018LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networkscited by 41
  30. 2024Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Drivingcited by 41
  31. 2025On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspectivecited by 41
  32. 2024AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learningcited by 40
  33. 2023Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perceptioncited by 38
  34. 2023Among Us: Adversarially Robust Collaborative Perception by Consensuscited by 37
  35. 2023Generative AI-driven Semantic Communication Networks: Architecture, Technologies and Applicationscited by 36
  36. 2024AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Drivingcited by 35
  37. 2025AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Drivingcited by 35
  38. 2024Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehiclescited by 33

50 most cited of 92 All 92 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAscited by 1
  2. 2025NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LACO: Adaptive Latent Communication for Collaborative Driving
  2. 2025FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems
  3. 2026ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
  4. 2026SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
  5. 2026GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic
  6. 2025Agentic Moderation: Multi-Agent Design for Safer Vision-Language Models
  7. 2026Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy
  8. 2025Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats