4 papers
LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents
Longtao Guo, Zelin Zhang, Kaifeng Huang +1
LLM-based web agents automate user tasks by observing webpages and executing browser actions on behalf of users. As these agents operate on real web services, login becomes a sensi…
Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions
Yang Shi, Jiaheng Fu, Yihe Huang +3
Large language models (LLMs) are increasingly deployed as autonomous agents that interact with external tools and services via the Model Context Protocol (MCP), a standardized inte…
Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach
Yuanheng Li, Zhuoyang Chen, Xiaoyun Liu +5
As large language models (LLMs) become increasingly capable, concerns over the unauthorized use of copyrighted and licensed content in their training data have grown, especially in…
Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environments
Congcong Chen, Xinyu Liu, Kaifeng Huang +2
Graph Neural Networks (GNNs) have marked significant impact in traffic state prediction, social recommendation, knowledge-aware question answering and so on. As more and more users…