AI RESEARCH
Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models
arXiv CS.CV
•
ArXi:2603.04846v2 Announce Type: replace The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial attacks against MLLMs typically rely on surrogate models trained within a single learning paradigm and perform independent optimisation in their respective feature spaces.