← Search

Kanghua Mo

2 accepted papers

2025

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

NeurIPS 2025poster

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, where adversaries can manipulate tool metadata---such as names,…

Cited by 0SourcecodeScholar
2025

Distraction is All You Need for Multimodal Large Language Model Jailbreaking

CVPR 2025highlight

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 mechan…

Cited by 1SourcePDFScholar