Curv-Tail：基于离散包长度编码和Lorentz原型的高效长尾加密流量分类
Curv-Tail: Lightweight Long-Tailed Encrypted Traffic Classification with Discrete Packet-Length Encoding and Lorentz Prototypes
浏览论文内容
中文总结 AI 辅助
Curv-Tail提出轻量级端到端框架，通过混合分辨率包长度编码和Lorentz原型，在有限计算下提升长尾加密流量分类性能，显著超越基线并降低参数与推理开销。
中文摘要 AI 辅助
长尾加密流量分类要求在有限的计算预算下准确识别不频繁出现的类别。我们提出了Curv-Tail，一个轻量级的端到端包-字节框架，无需单独的预训练阶段。混合分辨率分词在有限范围内保留精确的包长度标识，并对较大值进行粗化以限制词汇量。一个辅助目标在池化之前从上下文包特征预测观察到的长度标记，鼓励在流级监督之外保留长度标记。紧凑的时间编码器处理包序列和方向性字节补丁，具有共享可学习曲率幅度的Lorentz原型对其融合表示进行分类。在自然类别频率下的NUDT-Mobile和DataCon-Website数据集上，Curv-Tail实现了三种子平均Tail-F1分数分别为85.70%和46.30%，分别超过最强评估基线2.91和1.89个百分点。在RTX 4090上使用FP32和批量大小256的300类性能分析中，Curv-Tail使用的参数减少98.48%，批量推理吞吐量是MM4Flow的10.2倍。
英文摘要
Long-tailed encrypted traffic classification requires accurate recognition of infrequent classes under limited computational budgets. We propose Curv-Tail, a lightweight, end-to-end packet--byte framework trained without a separate pretraining stage. Mixed-resolution tokenization preserves exact packet-length identities within a bounded range and coarsens larger values to limit the vocabulary. An auxiliary objective predicts observed length tokens from contextual packet features before pooling, encouraging length-token retention beyond flow-level supervision. Compact temporal encoders process packet sequences and directional byte patches, and Lorentz prototypes with a shared learnable curvature magnitude classify their fused representation. On NUDT-Mobile and DataCon-Website under natural class frequencies, Curv-Tail achieves three-seed mean Tail-F1 scores of 85.70% and 46.30%, exceeding the strongest evaluated baselines by 2.91 and 1.89 percentage points, respectively. In 300-class profiling on an RTX 4090 with FP32 and batch size 256, Curv-Tail uses 98.48% fewer parameters and achieves 10.2 times the batch inference throughput of MM4Flow.
发表机构
- National University of Defense Technology（国防科技大学）
- Hunan First Normal University（湖南第一师范学院）
机构由 AI 辅助整理，请以论文原文为准。
