MLLM security
NeurIPS 2025 | Cracking Closed-Source Multimodal Models: A Novel Adversarial Attack via Optimal Feature Alignment
Introduction In recent years, Multimodal Large Language Models (MLLMs) have made remarkable breakthroughs, showing strong capabilities in visual understanding, cross-modal reasoning, and image captioning. However, with wider deployment in real-world scenarios, security risks have become a growing concern. Research indicates that MLLMs inherit adversarial vulnerabilities from their visual encoders, making