Caini Chang

Papers on Lattice

Total citations

Topics

h-index

Research focus

Constitutional AI & AI Ethics (1)Red-Teaming & Adversarial Robustness (1)Tool Use & Agents (1)

Frequent co-authors

Wenpeng Xing (1)Zhonghao Qi (1)Yupeng Qin (1)Yilin Li (1)

Papers (1)

Aug 14, 2025

Wenpeng Xing +8Aug 14, 2025

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI

LLM-tool integrations are riddled with security holes, but MCP-GUARD offers a practical, multi-layered defense that achieves 96% accuracy in detecting adversarial prompts.

Wenpeng Xing, Zhonghao Qi, Yupeng Qin +67

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness Tool Use & Agents

Search

Caini Chang

Research focus

Frequent co-authors

Papers (1)