Agents extend their capabilities through reusable skills that package instructions, executable code, and resources. Composing these skills enables complex task workflows, but their dependencies can also connect malicious operations across skills, making their combined intent difficult to identify through individual-pac...
Qi-Cheng Zhao, Sheng-Fang Zhai, Qing-Ni Shen et al.· 0 citations
ACLE-MCP is presented, an invocation-scoped architecture that couples delegated authorization, workload appraisal, and resource-side execution admission that indicates that invocation-time binding between call authority and current workload state is a practical complement to OAuth-protected remote tool use.
Zhi-Yang Ding, Yang Luo, Guang-Pu Chen et al.· 1 citation
JITterFlip is presented, the first BFA targeting the host-side JIT serving control plane of GPU-based LLM inference, and develops a decision-guided fault-vulnerable code analysis that enables both gibberish output generation and a correct-output sponge attack.
Tai-Rui Wang, Zhi Zhang, Yan-Song Gao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.