7 papers
Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
Yuxi Sun, Wenbo Shang, Wei Gao +2
In RAG-based fact-checking, LLMs are increasingly used as verifiers to check given claims against retrieved evidence. Their parametric knowledge can induce pre-evidence tendencies…
Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
Charoes Huang, Xin Huang, Ngoc Phu Tran +1
The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration betwe…
Are AI-assisted Development Tools Immune to Prompt Injection?
Charoes Huang, Xin Huang, Amin Milani Fard
Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose sensitive data, and trigger unau…
Auditing MCP Servers for Over-Privileged Tool Capabilities
Charoes Huang, Xin Huang, Amin Milani Fard
The Model Context Protocol (MCP) has emerged as a standard for connecting Large Language Models (LLMs) to external tools and data. However, MCP servers often expose privileged capa…
LLMTailor: A Layer-wise Tailoring Tool for Efficient Checkpointing of Large Language Models
Minqiu Sun, Xin Huang, Luanzheng Guo +3
Checkpointing is essential for fault tolerance in training large language models (LLMs). However, existing methods, regardless of their I/O strategies, periodically store the entir…
Scrutinizing Variables for Checkpoint Using Automatic Differentiation
Xin Huang, Weiping Zhang, Shiman Meng +4
Checkpoint/Restart (C/R) saves the running state of the programs periodically, which consumes considerable system resources. We observe that not every piece of data is involved in…