Abstract
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 (source onsumpton Red-aming for LVLMs), the first approach for exploiting visual modalities to trigger unbounded RCAs red-teaming. First, we present , 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. E