Year: 2025
Type: conference-paper
Abstract: With the emergence of strong vision language capabilities, multimodal large language models (MLLMs) have demonstrated tremendous potential for real-world applications.However, the security vulnerabilities exhibited by the visual modality pose significant challenges to deploying such models in open-world environments.Recent studies have successfully induced harmful responses from target MLLMs by encoding harmful textual semantics directly into visual inputs.However, in these approaches, the visual modality primarily serves as a trigger for unsafe behavior, often exhibiting semantic ambiguity and lacking grounding in realistic scenarios.In this work, we define a novel setting: vision-centric jailbreak, where visual information serves as a necessary component in constructing a complete and realistic jailbreak context.Building on this setting, we propose the VisCo (Visual Contextual) Attack.VisCo fabricates contextual dialogue using four distinct vision-focused strategies, dynamically generating auxiliary images when necessary to construct a vision-centric jailbreak scenario.To maximize attack effectiveness, it incorporates automatic toxicity obfuscation and semantic refinement to produce a final attack prompt that reliably triggers harmful responses from the target black-box MLLMs.Specifically, VisCo achieves a toxicity score of 4.78 and an Attack Success Rate (ASR) of 85% on MM-SafetyBench against GPT-4o, significantly outperforming the baseline, which achieves a toxicity score of 2.48 and an ASR of 22.2%.Code: https://github.com/ Dtc7w3PQ/Visco-Attack.Warning: This paper contains offensive and unsafe responses.
Authors: Miao Ziqi, Yi Ding, Lijun Li, Jing Shao
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4416036834