研究人员正在开发能够欺骗自动驾驶所使用的视觉语言模型（VLM）的对抗性补丁。这些补丁在物理应用时，可能导致系统漏检行人或误解道路状况。研究表明，不同VLM架构之间的可迁移性很高，这意味着为一种模型优化的攻击仍然可以有效地对抗其他模型，从而带来重大的安全风险。 AI
影响 新研究突显了自动驾驶感知系统存在的重大漏洞，可能需要新的防御机制来对抗对抗性攻击。
排序理由 该集群包含多篇arXiv论文，详细介绍了针对自动驾驶视觉语言模型的对抗性攻击研究。
AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Recent advances in vision language action (VLA) models have shown remarkable potential for autonomous driving by directly mapping multimodal inputs to control signals. However, previous VLA-based methods have not explicitly exploited the critic capability of VLAs to refine drivin…
arXiv:2604.27366v1 Announce Type: new Abstract: Recent advances in vision language action (VLA) models have shown remarkable potential for autonomous driving by directly mapping multimodal inputs to control signals. However, previous VLA-based methods have not explicitly exploite…
arXiv:2604.27414v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversar…
Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial attacks, especially whether such attacks tra…
arXiv:2604.23105v1 Announce Type: new Abstract: Deep learning drives major advances in autonomous driving (AD), where object detectors are central to perception. However, adversarial attacks pose significant threats to the reliability and safety of these systems, with physical ad…
arXiv:2604.22552v1 Announce Type: new Abstract: Physical adversarial patch attacks critically threaten pedestrian detection, causing surveillance and autonomous driving systems to miss pedestrians and creating severe safety risks. Despite their effectiveness in controlled setting…
Physical adversarial patch attacks critically threaten pedestrian detection, causing surveillance and autonomous driving systems to miss pedestrians and creating severe safety risks. Despite their effectiveness in controlled settings, existing physical attacks face two major limi…