Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
Yibo Zhang, Tianrong Guan, Liang Lin +3
Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activation depends on explicit trigger…
cs.CR2026
MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
Zhenhong Zhou, Yuanhe Zhang, Hongwei Cai +6
The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trus…