EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingGPULanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Overloading Large Vision-Language Models for Jailbreaking
Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document analysis systems, and embodied agents. H…
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from…
Safety AlignmentTraining Strategies for Autoencoder-based Detection of False Data Injection Attacks
The security of energy supply in a power grid critically depends on the ability to accurately estimate the state of the system. However, manipulated power flow measurements can potentially hide overloads and bypass the b…
Information overload and environmental degradation: learning from H.A. Simon and W. Wenders
This paper discusses the relevance of information overload for explaining environmental degradation. Our argument goes that information overload and detachment from nature, caused by energy abundance, have made individua…
A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about their reliability in real-world use. Wh…
Visual Question AnsweringAdversarial RobustnessImage Captioning