Xin Hu

This paper analyzes the security vulnerabilities of the Model Context Protocol (MCP), identifying tool poisoning as the most critical client-side threat, and proposes a multi-layered defense strategy.

The paper empirically analyzes the susceptibility of seven widely used AI-assisted development tools (MCP clients) to prompt injection via tool-poisoning, revealing significant disparities in their security guardrails.

The paper introduces mcp-sec-audit, a comprehensive toolkit that assesses Model Context Protocol (MCP) servers for over-privileged and insecure tool capabilities.

This paper introduces a component-centric framework and a novel detector, Connor, to understand and detect sophisticated, multi-component attacks targeting the Model Context Protocol (MCP) servers.

The paper introduces Constraint-Guided Semantic Testing (ConSeT), a novel framework that systematically finds critical, pre-authentication vulnerabilities in 5G User Equipment (UE) by exploiting semantically inconsistent, yet syntactically valid, RRC messages.

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compression with Hindsight Response Replay.

The paper introduces a diagnostic testbed, PAVE, to evaluate how LLMs arbitrate between their internal knowledge and retrieved evidence during fact-checking, revealing that this arbitration is unreliable and highly model-dependent.

The paper introduces MiCU, a domain-specific LLM that significantly improves smart home command understanding, especially for ambiguous commands, by synthesizing training data and optimizing the model for efficiency.

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searchable memory.

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.