SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving

• URL: http://arxiv.org/abs/2510.18123v1
• Date: Mon, 20 Oct 2025 21:41:28 GMT
• Title: SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving
• Authors: Xiangbo Gao, Tzu-Hsiang Lin, Ruojing Song, Yuheng Wu, Kuan-Ru Huang, Zicheng Jin, Fangzhou Lin, Shinan Liu, Zhengzhong Tu,
• Abstract summary: Collaborative driving systems leverage vehicle-to-everything (V2X) communication across multiple agents to enhance driving safety and efficiency.<n>Traditional V2X systems face persistent challenges, including high bandwidth demands, semantic loss, and interoperability issues.<n>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.
• Score: 16.620713493180165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions [20.73038673205127]
  We provide a transition-oriented view from Secure Agentic AI to a Secure Agentic Web.<n>We first summarize a component-aligned threat taxonomy covering prompt abuse, environment injection, memory attacks, toolchain abuse, model tampering, and agent network attacks.<n>We then review defense strategies, including prompt hardening, safety-aware decoding, privilege control for tools and APIs, runtime monitoring, continuous red-teaming, and protocol-level security mechanisms.
  arXiv  Detail & Related papers  (2026-03-02T07:44:18Z)
• Multi-Agent-Driven Cognitive Secure Communications in Satellite-Terrestrial Networks [58.70163955407538]
  Malicious eavesdroppers pose a serious threat to private information via satellite-terrestrial networks (STNs)<n>We propose a cognitive secure communication framework driven by multiple agents that coordinates spectrum scheduling and protection through real-time sensing.<n>We exploit generative adversarial networks to produce adversarial matrices, and employ learning-aided power control to set real and adversarial signal powers for protection layer.
  arXiv  Detail & Related papers  (2026-01-06T10:30:41Z)
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows [77.95511352806261]
  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.<n>We propose OS-Sentinel, a novel hybrid safety detection framework that combines a Formal Verifier for detecting explicit system-level violations with a Contextual Judge for assessing contextual risks and agent actions.
  arXiv  Detail & Related papers  (2025-10-28T13:22:39Z)
• UNCAP: Uncertainty-Guided Planning Using Natural Language Communication for Cooperative Autonomous Vehicles [79.10221881250759]
  Uncertainty-Guided Natural Language Cooperative Autonomous Planning (UNCAP) is a vision-language model-based planning approach.<n>It enables CAVs to communicate via lightweight natural language messages while explicitly accounting for perception uncertainty in decision-making.<n> Experiments across diverse driving scenarios show a 63% reduction in communication bandwidth with a 31% increase in driving safety score, a 61% reduction in decision uncertainty, and a four-fold increase in collision distance margin.
  arXiv  Detail & Related papers  (2025-10-14T21:09:09Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• LangCoop: Collaborative Driving with Language [13.25814019477039]
  LangCoop is a new paradigm for collaborative autonomous driving that leverages natural language as a compact yet expressive medium for inter-agent communication.<n>LangCoop achieves a remarkable 96% reduction in communication bandwidth ( 2KB per message) compared to image-based communication.
  arXiv  Detail & Related papers  (2025-04-18T02:03:14Z)
• Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks [59.300698230887114]
  Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses.<n>We propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues.
  arXiv  Detail & Related papers  (2025-02-28T21:10:03Z)
• Machine Learning-Based Malicious Vehicle Detection for Security Threats and Attacks in Vehicle Ad-hoc Network (VANET) Communications [0.48951183832371004]
  Blackhole attacks are significant threats to Vehicle Ad-hoc Network (VANET) In this paper, we propose a machine learning-based approach for blackhole detection in VANET.
  arXiv  Detail & Related papers  (2024-01-16T06:01:02Z)
• OblivIO: Securing reactive programs by oblivious execution with bounded traffic overheads [0.0]
  Traffic analysis attacks remain a significant problem for online security.<n>Despite online services increasingly using encrypted traffic, the shape of the traffic is not hidden.<n>We present OblivIO, a secure language for writing reactive programs driven by network events.
  arXiv  Detail & Related papers  (2023-01-19T15:59:33Z)
• Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer [28.15612357340141]
  We propose a safety-enhanced autonomous driving framework, named Interpretable Sensor Fusion Transformer(InterFuser) We process and fuse information from multi-modal multi-view sensors for achieving comprehensive scene understanding and adversarial event detection. Our framework provides more semantics and are exploited to better constrain actions to be within the safe sets.
  arXiv  Detail & Related papers  (2022-07-28T11:36:21Z)
• Learning to Communicate and Correct Pose Errors [75.03747122616605]
  We study the setting proposed in V2VNet, where nearby self-driving vehicles jointly perform object detection and motion forecasting in a cooperative manner. We propose a novel neural reasoning framework that learns to communicate, to estimate potential errors, and to reach a consensus about those errors.
  arXiv  Detail & Related papers  (2020-11-10T18:19:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.