Listen to Minority: Encrypted Traffic Classification for Class Imbalance with Contrastive Pre-Training

no code implementations • 31 Aug 2023 • Xiang Li, Juncheng Guo, Qige Song, Jiang Xie, Yafei Sang, Shuyuan Zhao, Yongzheng Zhang

Despite some existing learning-based ETC methods showing promising results, three-fold limitations still remain in real-world network environments, 1) label bias caused by traffic class imbalance, 2) traffic homogeneity caused by component sharing, and 3) training with reliance on sufficient labeled traffic.

Pseudo Label Traffic Classification