学习互视图信息图用于自适应对抗协同感知
Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
把多车协同感知中的特征融合过程建模为互视图信息图，并用时序图学习生成伪造风险图来搜索攻击位置与时机，这一「图表示+熵感知搜索」的框架可直接迁移到对 BEV 融合、V2X 协同检测等视觉系统的红队测试与防御加固。
原文依据 a novel adaptive adversarial CP framework learning to capture vulnerability knowledge disclosed by different defensive CP systems from a unified mutual view information graph
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论协同感知（CP）使网联自动驾驶车辆（CAV）之间能够共享数据，从而提升行驶安全性。然而，CP 系统易受对抗攻击影响，恶意代理可通过特征级扰动伪造虚假目标。现有防御系统通过比较协同检测结果与自车检测结果进行基于阈值的共识验证。但这些防御仍难以抵御更复杂的攻击策略，此类策略可利用两个关键弱点：（i）面对在时序与目标区域上经过系统优化的攻击时缺乏鲁棒性；（ii）共享协同数据中隐含的置信度信息会无意间泄露脆弱性知识。本文提出 MVIG 攻击，一种新颖的自适应对抗 CP 框架，它从统一的互视图信息图（MVIG）表示中学习并捕获不同防御型 CP 系统所泄露的脆弱性知识。该方法将 MVIG 表示与时序图学习相结合，生成不断演化的伪造风险图，并采用熵感知的脆弱性搜索来优化攻击位置、时机与持续性，从而实现可泛化到多种防御配置的自适应攻击。在 OPV2V 与 Adv-OPV2V 数据集上的大量评估表明，MVIG 攻击使最优防御的成功率最多下降 62%，同时在 29.9 FPS 下对持续性攻击的检测率降低 47%，揭示了 CP 系统中关键的安全缺口。代码将发布于 https://github.com/yihangtao/MVIG.git。
英文原文摘要 1609 字符
Collaborative perception (CP) enables data sharing among connected and autonomous vehicles (CAVs) to enhance driving safety. However, CP systems are vulnerable to adversarial attacks where malicious agents forge false objects via feature-level perturbations. Current defensive systems use threshold-based consensus verification by comparing collaborative and ego detection results. Yet, these defenses remain vulnerable to more sophisticated attack strategies that could exploit two critical weaknesses: (i) lack of robustness against attacks with systematic timing and target region optimization, and (ii) inadvertent disclosure of vulnerability knowledge through implicit confidence information in shared collaboration data. In this paper, we propose MVIG attack, a novel adaptive adversarial CP framework learning to capture vulnerability knowledge disclosed by different defensive CP systems from a unified mutual view information graph (MVIG) representation. Our approach combines MVIG representation with temporal graph learning to generate evolving fabrication risk maps and employs entropy-aware vulnerability search to optimize attack location, timing and persistence, enabling adaptive attacks with generalizability across various defensive configurations. Extensive evaluations on OPV2V and Adv-OPV2V datasets demonstrate that MVIG attack reduces defense success rates by up to 62% against state-of-the-art defenses while achieving 47% lower detection for persistent attacks at 29.9 FPS, exposing critical security gaps in CP systems. Code will be released at https://github.com/yihangtao/MVIG.git.