2 papers
cs.CV2026
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
Chenxi Li, Xianggan Liu, Dake Shen +9
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elici…
cs.CR2026
Secure and Efficient Access Control for Computer-Use Agents via Context Space
Haochen Gong, Chenxiao Li, Rui Chang +1
Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions…