Peizhi Niu

The paper introduces TurnGate, a response-aware defense mechanism that detects the earliest turn in a multi-turn dialogue where the accumulated interaction enables a harmful action, significantly improving malicious intent detection.

The paper introduces MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current state-of-the-art agents struggle with such personalized tool use.