2 citations · 5 across the 30 of their papers we have counts for
16 papers · 1 filter
UNBIND: UNlearning By INference-time Directional Steering for Code LLMs
Zhengyang Shan, Jiayun Xin, Yanjun Lin +7
Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is needed to…
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents
Zhengyang Shan, Xu Qian, Jiayun Xin +3
Large language model agents are becoming operational interfaces to files, memories, registries, and external tools. This deployment shift creates a new skill revocation problem: af…
Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks
Ying JinCheng, Minghui Xu, Yinhao Xiao +2
Large language models (LLMs) are safety-aligned before deployment to reduce harmful content generation. Yet neuron-level pruning attacks show that refusal can depend on a small set…
Bad company corrupts good morals: Understanding and Measuring Narrative-Induced Moral Reasoning Degradation in LLMs
Wanying Yu, Boyang Ma, Zhibo Eric Sun +2
Large language models are deployed in long-context, emotionally interactive environments like digital humans, AI companions, educational assistants, and counseling systems. Unlike…
"What Happens Locally, Leaks Globally": Detecting Privacy Leakage Risks in MCP Servers
Biwei Yan, Minghui Xu, Yijun Yang +4
The Model Context Protocol (MCP) has rapidly become the de facto standard for connecting large language models (LLMs) to external resources, but it also introduces a class of priva…
A Measurement Study of Cryptographic Misuse in Embodied AI Mobile Applications
Junchao Li, Xuelei Wang, Yuhang Huang +5
Embodied AI (EAI) mobile applications are evolving from auxiliary user interfaces into active control-path components, directly linking mobile-side cryptographic security to cyber-…
PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation
Zhijun Li, Minghui Xu, Huayi Qi +6
Retrieval-Augmented Generation (RAG) is essential for enhancing Large Language Models (LLMs) with external knowledge, but its reliance on cloud environments exposes sensitive data…
AgentDID: Trustless Identity Authentication for AI Agents
Minghui Xu, Xiaoyu Liu, Yihao Guo +3
AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In…
Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs
Minghui Xu, Qi Luo, Kun Li +1
Traditional ``row-count quality coefficient'' approaches fail to capture the nonlinear utility of data for Large Language Model (LLM) capabilities. We present a utility-aw…
SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection
Zhengyang Shan, Xu Qian, Jiayun Xin +5
Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detecti…
Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs
Qi Luo, Minghui Xu, Dongxiao Yu +1
Modern graph learning systems often combine links with text, as in citation networks with abstracts or social graphs with user posts. In such systems, text is usually easier to edi…
Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
Zhengyang Shan, Jiayun Xin, Yue Zhang +1
Code agents powered by large language models can execute shell commands on behalf of users, introducing severe security vulnerabilities. This paper presents a two-phase security an…
What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
Boyang Ma, Hechuan Guo, Peizhuo Lv +5
Embodied AI systems (e.g., autonomous vehicles, service robots, and LLM-driven interactive agents) are rapidly transitioning from controlled environments to safety critical real-wo…
When Skills Lie: Hidden-Comment Injection in LLM Agents
Qianli Wang, Boyang Ma, Minghui Xu +1
LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this documentation layer: when a Markdown…
Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool Descriptions
Zhihao Li, Boyang Ma, Xuelong Dai +4
The Model Context Protocol (MCP) enables large language models to invoke external tools through natural-language descriptions, forming the foundation of many AI agent applications.…
Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
Yueyan Dong, Minghui Xu, Qin Hu +5
Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing train…