paper-with-me

홈 › Papers

EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models

2025-04-11 · Minjae Seo, Myoungsung You, Junhee Lee, Jaehan Kim, Hwanjo Heo, Jintae Oh, Jinwoo Kim

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.

📄 PDF Abstract BibTeX arXiv:2504.08205

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingGPULanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Overloading Large Vision-Language Models for Jailbreaking

2026-07-03 · Haoyu Zhang, Yangyang Guo, Mohan Kankanhalli arxiv

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

2023-11-16 · Nan Xu, Fei Wang, Ben Zhou, Bang Zheng Li 외

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 Alignment

Training Strategies for Autoencoder-based Detection of False Data Injection Attacks

2020-05-14 · Chenguang Wang, Kaikai Pan, Simon Tindemans, Peter Palensky

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

2022-09-02 · Tommaso Luzzati, Ilaria Tucci, Pietro Guarnieri

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

2026-03-27 · Mujtaba Hussain Mirza, Antonio D'Orazio, Odelia Melamed, Iacopo Masi arxiv

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