AI 中文总结
本文提出行为信息泄露框架，分析Tor等四种匿名网络的暗网流量，发现不同网络行为泄露差异显著，明确主要泄露机制及服务变异性，为暗网流量分类提供新视角。
AI 中文摘要
现有暗网流量分类研究大多侧重预测准确率，却对加密服务可区分的行为机制缺乏深入理解。本文提出一种行为信息泄露框架，将流级流量分解为控制、结构和节奏描述符组，覆盖Tor、I2P、FreeNet和ZeroNet四种匿名网络。该框架结合归一化互信息分析、基于Random Forest的预测验证、结构-节奏交互分析，以及在泄露安全的重复分层交叉验证下的跨网络服务变异性评估。结果表明，不同匿名网络的行为泄露差异显著：Tor实现最高服务可分性，Macro-F1为0.7165，累积归一化泄露为3.9461；而FreeNet的综合泄露最低，为0.8744。报文大小组织、方向交换失衡、报文节奏及静默-突发行为是主要泄露机制。综合结构-节奏表示始终提供最强的网络内性能，而留一网络评估显示跨匿名架构的可迁移性有限。提出的服务变异性指数和泄露变异性指数进一步表明，视频服务表现出一致的网络特定可分性，而聊天和电子邮件服务在匿名网络对之间表现出更大的变异性。
英文摘要
Existing darknet traffic classification studies largely emphasize predictive accuracy while offering limited insight into the behavioral mechanisms that make encrypted services distinguishable. This paper proposes a behavioral information leakage framework that decomposes flow-level traffic into control, structural, and rhythmic descriptor groups across Tor, I2P, FreeNet, and ZeroNet. The framework combines normalized mutual information analysis with Random Forest-based predictive validation, structural-rhythmic interaction analysis, and cross-network service-variability evaluation under leakage-safe repeated stratified cross-validation. Results show that behavioral leakage varies considerably across anonymity networks. Tor achieves the highest service separability, with a Macro-F1 of 0.7165 and cumulative normalized leakage of 3.9461, whereas FreeNet exhibits the lowest combined leakage of 0.8744. Packet-size organization, directional exchange imbalance, packet tempo, and silence-burst behavior emerge as the main leakage mechanisms. The combined structural-rhythmic representation consistently provides the strongest within-network performance, while leave-one-network-out evaluation reveals limited transferability across anonymity architectures. The proposed Service Variability Index and Leakage Variability Index further show that video exhibits consistent network-specific separability, whereas chat and email demonstrate greater variability across anonymity-network pairs.
Comments21 pages, 7 figures, 6 tables
