Resource Consumption Red-Teaming for Large Vision-Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912607400624128 |
|---|---|
| author | Gao, Haoran Zhang, Yuanhe Zhou, Zhenhong Jiang, Lei Meng, Fanyu Xiao, Yujia Sun, Li Wang, Kun Liu, Yang Feng, Junlan |
| author_facet | Gao, Haoran Zhang, Yuanhe Zhou, Zhenhong Jiang, Lei Meng, Fanyu Xiao, Yujia Sun, Li Wang, Kun Liu, Yang Feng, Junlan |
| contents | Resource Consumption Attacks (RCAs) have emerged as a significant threat to the deployment of Large Language Models (LLMs). With the integration of vision modalities, additional attack vectors exacerbate the risk of RCAs in large vision-language models (LVLMs). However, existing red-teaming studies have mainly overlooked visual inputs as a potential attack surface, resulting in insufficient mitigation strategies against RCAs in LVLMs. To address this gap, we propose RECITE ($\textbf{Re}$source $\textbf{C}$onsumpt$\textbf{i}$on Red-$\textbf{Te}$aming for LVLMs), the first approach for exploiting visual modalities to trigger unbounded RCAs red-teaming. First, we present $\textit{Vision Guided Optimization}$, a fine-grained pixel-level optimization to obtain \textit{Output Recall Objective} adversarial perturbations, which can induce repeating output. Then, we inject the perturbations into visual inputs, triggering unbounded generations to achieve the goal of RCAs. Empirical results demonstrate that RECITE increases service response latency by over 26 $\uparrow$, resulting in an additional 20\% increase in GPU utilization and memory consumption. Our study reveals security vulnerabilities in LVLMs and establishes a red-teaming framework that can facilitate the development of future defenses against RCAs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18053 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Resource Consumption Red-Teaming for Large Vision-Language Models Gao, Haoran Zhang, Yuanhe Zhou, Zhenhong Jiang, Lei Meng, Fanyu Xiao, Yujia Sun, Li Wang, Kun Liu, Yang Feng, Junlan Cryptography and Security Computation and Language Resource Consumption Attacks (RCAs) have emerged as a significant threat to the deployment of Large Language Models (LLMs). With the integration of vision modalities, additional attack vectors exacerbate the risk of RCAs in large vision-language models (LVLMs). However, existing red-teaming studies have mainly overlooked visual inputs as a potential attack surface, resulting in insufficient mitigation strategies against RCAs in LVLMs. To address this gap, we propose RECITE ($\textbf{Re}$source $\textbf{C}$onsumpt$\textbf{i}$on Red-$\textbf{Te}$aming for LVLMs), the first approach for exploiting visual modalities to trigger unbounded RCAs red-teaming. First, we present $\textit{Vision Guided Optimization}$, a fine-grained pixel-level optimization to obtain \textit{Output Recall Objective} adversarial perturbations, which can induce repeating output. Then, we inject the perturbations into visual inputs, triggering unbounded generations to achieve the goal of RCAs. Empirical results demonstrate that RECITE increases service response latency by over 26 $\uparrow$, resulting in an additional 20\% increase in GPU utilization and memory consumption. Our study reveals security vulnerabilities in LVLMs and establishes a red-teaming framework that can facilitate the development of future defenses against RCAs. |
| title | Resource Consumption Red-Teaming for Large Vision-Language Models |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2507.18053 |