AI RESEARCH
VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts
arXiv CS.LG
•
ArXi:2604.06502v1 Announce Type: new Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges, we first propose the Multimodal Aggregated Feature Extraction (MAFE) framework that enables CLIP to handle long text and fuse multimodal information into unified representations. Through empirical analysis of MAFE-extracted features, we discover distinct distributional patterns between benign and malicious prompts.