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

arXiv: https://arxiv.org/abs/2504.08205 · HTML: https://mlsanity.com/paper/2504.08205/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 4 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Builds on (most cited first, 3 of 3)

- [Sponge Examples: Energy-Latency Attacks on Neural Networks](https://mlsanity.com/paper/2006.03463/) (2020)
- [Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images](https://mlsanity.com/paper/2401.11170/) (2024)
- [SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examples](https://mlsanity.com/paper/2312.09520/) (2023)

## Built on by (most cited first, 1 of 1)

- [Resource Consumption Threats in Large Language Models](https://mlsanity.com/paper/2603.16068/) (2026)

## Abstract (arXiv)

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.