Logo image
Back
TARL: Multi-task adaptive representation learning for secure encrypted traffic analysis
Journal article   Peer reviewed

TARL: Multi-task adaptive representation learning for secure encrypted traffic analysis

Mengmeng Ge, Likun Liu, Zhaowei Zhang, Hongyu Wang, Xiangzhan Yu, Yijia Xu, Ruitao Feng and Zhichao Hu
Computer Networks, Vol.288, pp.1-13
10/2026
DOI: https://doi.org/10.1016/j.comnet.2026.112646
Appears in  Recent Faculty of Science and Engineering Publications

Metrics

1 Record Views

Abstract

Encrypted traffic analysis Intrusion detection Multi-task learning Network security
The growth of encryption technology has made encrypted traffic analysis both increasingly critical and inherently challenging. Tasks such as intrusion detection, application classification, and encrypted web fingerprinting are vital to network security, yet are often studied in isolation using single-task models. This fragmented approach limits the ability to capture shared behavioral patterns and undermines generalization across tasks. In this paper, we propose TARL, a novel task-adaptive representation learning framework for secure encrypted traffic analysis. TARL combines a shared memory module for task-agnostic representation learning with a task-specific fusion mechanism for downstream adaptation. To support pretraining under encryption constraints, we introduce two self-supervised objectives: masked feature modeling and service-type prediction. We evaluate TARL on four real-world encrypted traffic tasks. Results show that TARL consistently outperforms single-task and multi-task baselines, achieving strong generalization and per-task accuracy. Ablation studies further validate the complementary design of shared and task-specific modules.

Details

Logo image