Model Context Protocol (MCP) is rapidly emerging as a standard interface for connecting large language model (LLM) applications to external tools. An MCP tool exposes two semantic views of the same functionality: a developer-provided description that guides the LLM's tool selection, and an implementation that determine...
Heng-Kai Ye, Zhe-Chang Zhang, Rui-Bo Lu et al.· Proceedings of the 2026 ACM...· 0 citations
PIMiner is developed, an agentic system for prompt injection red-teaming that builds a strategy library from scratch during training and can be directly transferred to a previously unseen target LLM without additional training at test time.
Yan-Ting Wang, Chenlong Yin, Runpeng Geng et al.· 0 citations
LongPIBench is introduced, a long-context benchmark for prompt injection covering 4 realistic application scenarios: paper peer review, resume screening, code review, and email summary, and the evaluation results reveal significant vulnerabilities of prompt injection defenses under long-context settings.
Yupei Liu, Yuqi Jia, N. Gong 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.