MiaoHoh/TS-GAN-A-Lightweight-Cross-Domain-Adaptation-for-Network-Intrusion-Detection-Code: TS-GAN-A-Lightweight-Cross-Domain-Adaptation-for-Network-Intrusion-Detection-Code

Read full text Summarise with VIRAT
Authors: MiaoHoh
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

TS-GAN: A lightweight framework for Real-time Cross-Domain IDS. Integrates Knowledge Distillation for compression and Time-Series GANs for unsupervised domain adaptation. Resolves performance degradation from distribution shifts (e.g., UNSW-NB15 to CIC-IDS2017), achieving a 90.13% F1-score with only 1.42ms latency.

Fields of Study & Subjects

Network Security and Intrusion Detection Network Packet Processing and Optimization Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN