EO-VLM：基于视觉语言模型引导的视觉模型能量过载攻击
EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models
AI总结：
本文提出EO-VLM框架，利用视觉语言模型提示生成人眼不可察觉的对抗图像，在不依赖目标模型内部信息的情况下使视觉模型GPU能耗最多增加50%，揭示了视觉模型在资源可用性方面的关键安全漏洞。
摘要：
视觉模型越来越多地部署在自动驾驶和闭路电视监控等关键应用中，但它们仍然容易受到资源消耗型攻击。本文提出一种新颖的能量过载攻击，利用视觉语言模型（VLM）提示生成针对视觉模型的对抗图像。这些图像虽然人眼难以察觉，却能显著增加各种视觉模型的GPU能量消耗，威胁这些系统的可用性。我们的框架EO-VLM（通过VLM实现能量过载）具有模型无关性，即不受目标视觉模型架构或类型的限制。通过利用DALL-E 3等VLM中缺乏安全过滤器的问题，我们在不需要目标视觉模型先验知识或内部结构的情况下生成对抗噪声图像。实验表明能量消耗最多增加50%，揭示了当前视觉模型中一个关键漏洞。
英文摘要：
Vision models are increasingly deployed in critical applications such as autonomous driving and CCTV monitoring, yet they remain susceptible to resource-consuming attacks. In this paper, we introduce a novel energy-overloading attack that leverages vision language model (VLM) prompts to generate adversarial images targeting vision models. These images, though imperceptible to the human eye, significantly increase GPU energy consumption across various vision models, threatening the availability of these systems. Our framework, EO-VLM (Energy Overload via VLM), is model-agnostic, meaning it is not limited by the architecture or type of the target vision model. By exploiting the lack of safety filters in VLMs like DALL-E 3, we create adversarial noise images without requiring prior knowledge or internal structure of the target vision models. Our experiments demonstrate up to a 50% increase in energy consumption, revealing a critical vulnerability in current vision models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
