Adapting Large Language Models for Encrypted Traffic Analysis Services: An Efficient Realization With Mixture of LoRA Experts
IEEE Transactions on Services Computing · 2026-03 · 19 (2) · 906-919
DOI: 10.1109/tsc.2026.3671484 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2026-03. Verfasst von Yi Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben.
Abstract (Originalsprache)
As encrypted traffic grows, traditional rule-based and deep learning methods struggle with engineering costs and encryption complexity. While Large Language Models (LLMs) offer promise for traffic analysis via pre-trained feature learning, they face challenges in handling diverse tasks, retaining pre-training knowledge, and adapting efficiently. To address these issues, we propose a new traffic representation learning method and a new Parameter-Efficient Fine-Tuning (PEFT) method for multi-task encrypted traffic analysis services, called TrafficLLM. TrafficLLM alleviates task heterogeneity by utilizing a universal multi-task prompt template and addresses pre-training knowledge forgetting by integrating Singular Value Decomposition based Low-Rank Adaptation (SVD-LoRA). To further reduce the cost of adapting to multiple tasks, we combine the strengths of the Mixture of Experts (MoE) for multi-task learning with SVD-LoRA for PEFT, enabling efficient multi-task traffic analysis. Additionally, we introduce task-aware gating functions to dynamically assign different weights to experts, facilitating the efficient fusion of expert knowledge. Comprehensive experiments on 7 datasets across 5 downstream tasks demonstrate that TrafficLLM delivers superior analysis performance and resource efficiency compared to state-of-the-art models, including DeepSeek, NetGPT, ET-BERT, and TFE-GNN. Detailed analysis of throughput, memory usage, and latency further highlights the practical advantages of TrafficLLM.
Zitieren
APA
Liu, Y., Zheng, X., Cai, C., Yuan, X., & Wang, C. (2026). Adapting Large Language Models for Encrypted Traffic Analysis Services: An Efficient Realization With Mixture of LoRA Experts. IEEE Transactions on Services Computing, 19(2), 906-919. https://doi.org/10.1109/tsc.2026.3671484
Vancouver
Liu Y, Zheng X, Cai C, Yuan X, Wang C. Adapting Large Language Models for Encrypted Traffic Analysis Services: An Efficient Realization With Mixture of LoRA Experts. IEEE Transactions on Services Computing. 2026;19(2):906-919. doi:10.1109/tsc.2026.3671484
BibTeX
@article{Liu2026,
author = {Liu, Yi and Zheng, Xiang and Cai, Chengjun and Yuan, Xingliang and Wang, Cong},
title = {Adapting Large Language Models for Encrypted Traffic Analysis Services: An Efficient Realization With Mixture of LoRA Experts},
journal = {IEEE Transactions on Services Computing},
year = {2026},
volume = {19},
number = {2},
pages = {906--919},
doi = {10.1109/tsc.2026.3671484}
}
EUVIMED