AIBearisharXiv – CS AI · Mar 67/10
🧠
Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
Researchers discovered a new vulnerability in multimodal large language models where specially crafted images can cause significant performance degradation by inducing numerical instability during inference. The attack method was validated on major vision-language models including LLaVa, Idefics3, and SmolVLM, showing substantial performance drops even with minimal image modifications.