研究人员开发了AirflowAttack，一种用于红外遥感视觉语言模型（VLMs）的对抗性扰动的新颖方法。该攻击利用热空气湍流，合成合理的空气流动模式来欺骗VLMs。在对六个最先进的VLMs进行测试时，AirflowAttack将场景分类准确率降低了高达38.2%，并矛盾地增加了模型的置信度，使其将扰动解释为真实的热证据。 AI
影响 暴露了红外VLMs的关键漏洞，可能影响其在安全关键应用中的部署。
排序理由 该集群包含一篇详细介绍新型对抗攻击方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.06485v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the fir…
Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs a…