TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
The proposed TDDM-Melatt, a disentangled memory-based traffic classification framework with diffusion-based data augmentation, provides a new and effective technical pathway for encrypted traffic classification in real-world network environments.
Zelang Chen, Qiming Yu, Zijia Song et al.
· 0 citations