The Internet of Agents (IoA) is emerging as a paradigm in which AI agents communicate and collaborate across organizational boundaries, attracting growing attention from both industry and standards communities. However, designing an agent communication protocol that can be deployed at both Internet and intranet scales...
Xiang Li, Yu-Qi Qiu, Zu-Yao Xu et al.· Proceedings of the 2026 ACM...· 0 citations
The results show that multi-SP vulnerabilities are both prevalent and systematically underreported, motivating stronger patch-completeness awareness, improved vulnerability database curation, and relation-aware security tooling.
Fang-Yuan Zhang, Lyuye Zhang, Lingling Fan et al.· 0 citations
These results show that benign execution trajectories can expose proprietary procedural knowledge, and SigLeak, a black-box framework that exploits recurring skill signatures in agent behavior, outperforms or matches three baselines in nearly every setting.
ColluSkill is proposed, a collusive multi-skill-chain attack framework that decomposes a complete malicious intent into interdependent sub-payloads embedded in independently packaged skills and employs LLM-based chain planning and scanner-feedback refinement to preserve chain-level attack semantics.
Pu-Yu Zeng, Simeng Qin, Jingzhi Li et al.· 1 citation
KubeCap, a framework for Kubernetes capability minimization, is proposed and Evaluation on 10 representative Go-based Kubernetes projects shows an average capability reduction rate of 54.97%, outperforming rapid type analysis and class hierarchy analysis baselines while maintaining practical analysis cost.
Yuhao Liu, Yingnan Zhou, Weijie Liu 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.
