四川大学学报（自然科学版）2026，Vol.63Issue(3)：531-539,9.DOI:10.19907/j.0490-6756.250329
基于动态图神经网络的Tor节点分类方法
A Tor node classification method based on dynamic graph neural networks
摘要
Abstract
Tor(The onion router)is an anonymous communication network based on multi-layer encryption and distributed routing technology,which is widely used for privacy protection.However,its high anonymity also renders the network a breeding ground for Darknet activities,posing severe threats to national security and social stability.Due to the diversity of node functions and network complexity,effective node classifica-tion has become a critical research topic.This paper proposes a Tor node classification method utilizing Dy-namic Self-Attention Temporal Graph Neural Networks(DySAT).This approach analyzes the historical as-sociation graph of Tor relay nodes and employs a spatiotemporal dual-attention mechanism to simultaneously capture node performance and security indicators.Experiments validate the effectiveness of the proposed method by selecting high-quality nodes and benchmarking performance against normal circuits.Compared with Tor's default circuit construction algorithm,the probability of selecting malicious nodes is reduced from 6.2%to 1.8%,and the average latency drops from 0.478 s to 0.389 s.Consequently,this method provides a new technical approach for Darknet governance,vulnerable node identification,and mitigation,helping to enhance network security capabilities and contain illegal activities on the Darknet.关键词
Tor网络/节点分类/动态神经网络/性能评估Key words
Tor network/node classification/dynamic neural network/performance evaluation分类
信息技术与安全科学引用本文复制引用
陈周国,陈振兴,李欣泽,丁建伟,孙恩博,谢相菊,李旭升..基于动态图神经网络的Tor节点分类方法[J].四川大学学报（自然科学版）,2026,63(3):531-539,9.基金项目
国家重点研发项目(2023YFB3106600) （2023YFB3106600）
