5 papers
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…
Second-Order Convergence in Private Stochastic Non-Convex Optimization
Youming Tao, Zuyuan Zhang, Dongxiao Yu +3
We investigate the problem of finding second-order stationary points (SOSP) in differentially private (DP) stochastic non-convex optimization. Existing methods suffer from two key…
Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things
Ye Cheng, Minghui Xu, Yue Zhang +7
Access control in the Internet of Things (IoT) is becoming increasingly complex, as policies must account for dynamic and contextual factors such as time, location, user behavior,…
Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
Senmao Qi, Yifei Zou, Peng Li +3
Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security im…
EC-Chain: Cost-Effective Storage Solution for Permissionless Blockchains
Minghui Xu, Hechuan Guo, Ye Cheng +3
Permissionless blockchains face considerable challenges due to increasing storage demands, driven by the proliferation of Decentralized Applications (DApps). This paper introduces…