Kanghua Mo

Zuopeng Yang, Jiluan Fan, Anli Yan et al.

Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce vulnerabilities, which may be exploited to bypass safety mechanisms. To address this, we analyze the relationship between image content and task and find that the complexity of subimages, rather than their content, is key. Building on this insight, we propose the Distraction Hypothesis, followed by a novel framework called Contrasting Subimage Distraction Jailbreaking (CS-DJ), to achieve jailbreaking by disrupting MLLMs alignment through multi-level distraction strategies. CS-DJ consists of two components: structured distraction, achieved through query decomposition that induces a distributional shift by fragmenting harmful prompts into sub-queries, and visual-enhanced distraction, realized by constructing contrasting subimages to disrupt the interactions among visual elements within the model. This dual strategy disperses the model's attention, reducing its ability to detect and mitigate harmful content. Extensive experiments across five representative scenarios and four popular closed-source MLLMs, including GPT-4o-mini, GPT-4o, GPT-4V, and Gemini-1.5-Flash, demonstrate that CS-DJ achieves average success rates of 52.40% for the attack success rate and 74.10% for the ensemble attack success rate. These results reveal the potential of distraction-based approaches to exploit and bypass MLLMs' defenses, offering new insights for attack strategies.

Kanghua Mo, Li Hu, Yucheng Long et al.

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface: adversaries can manipulate tool metadata -- such as names, descriptions, and parameter schemas -- to influence agent behavior. We identify this as a new and stealthy threat surface that allows malicious tools to be preferentially selected by LLM agents, without requiring prompt injection or access to model internals. To demonstrate and exploit this vulnerability, we propose the Attractive Metadata Attack (AMA), a black-box in-context learning framework that generates highly attractive but syntactically and semantically valid tool metadata through iterative optimization. Our attack integrates seamlessly into standard tool ecosystems and requires no modification to the agent's execution framework. Extensive experiments across ten realistic, simulated tool-use scenarios and a range of popular LLM agents demonstrate consistently high attack success rates (81\%-95\%) and significant privacy leakage, with negligible impact on primary task execution. Moreover, the attack remains effective even under prompt-level defenses and structured tool-selection protocols such as the Model Context Protocol, revealing systemic vulnerabilities in current agent architectures. These findings reveal that metadata manipulation constitutes a potent and stealthy attack surface, highlighting the need for execution-level security mechanisms that go beyond prompt-level defenses.