arXiv CS AI
techLean Left
Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimizationtranslating…
arXiv:2609.05889v1 Announce Type: new
Abstract: Resource-exhaustion attacks against autoregressive vision-language models (VLMs) typically assume unimodal threat models, treating the image branch as the primary optimization surface while holding user-visible prompts fixed. Even…
Keywords#Models#Vision-Language Models#Resource-Exhaustion Attacks#Optimization#Joint