Saved in:
Bibliographic Details
Main Authors: Hu, Haoyang, Huang, Xun, Wu, Chenyu, Liu, Shiwen, Lian, Zhichao, Zhang, Shuangquan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.10327
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916954218954752
author Hu, Haoyang
Huang, Xun
Wu, Chenyu
Liu, Shiwen
Lian, Zhichao
Zhang, Shuangquan
author_facet Hu, Haoyang
Huang, Xun
Wu, Chenyu
Liu, Shiwen
Lian, Zhichao
Zhang, Shuangquan
contents Intrusion detection systems (IDS) are widely used to maintain the stability of network environments, but still face restrictions in generalizability due to the heterogeneity of network traffics. In this work, we propose BERTector, a new framework of joint-dataset learning for IDS based on BERT. BERTector integrates three key components: NSS-Tokenizer for traffic-aware semantic tokenization, supervised fine-tuning with a hybrid dataset, and low-rank adaptation for efficient fine-tuning. Experiments show that BERTector achieves state-of-the-art detection accuracy, strong generalizability, and excellent robustness. BERTector achieves the highest accuracy of 99.28% on NSL-KDD and reaches the average 80% detection success rate against four perturbations. These results establish a unified and efficient solution for modern IDS in complex and dynamic network environments.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10327
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BERTector: An Intrusion Detection Framework Constructed via Joint-dataset Learning Based on Language Model
Hu, Haoyang
Huang, Xun
Wu, Chenyu
Liu, Shiwen
Lian, Zhichao
Zhang, Shuangquan
Cryptography and Security
Intrusion detection systems (IDS) are widely used to maintain the stability of network environments, but still face restrictions in generalizability due to the heterogeneity of network traffics. In this work, we propose BERTector, a new framework of joint-dataset learning for IDS based on BERT. BERTector integrates three key components: NSS-Tokenizer for traffic-aware semantic tokenization, supervised fine-tuning with a hybrid dataset, and low-rank adaptation for efficient fine-tuning. Experiments show that BERTector achieves state-of-the-art detection accuracy, strong generalizability, and excellent robustness. BERTector achieves the highest accuracy of 99.28% on NSL-KDD and reaches the average 80% detection success rate against four perturbations. These results establish a unified and efficient solution for modern IDS in complex and dynamic network environments.
title BERTector: An Intrusion Detection Framework Constructed via Joint-dataset Learning Based on Language Model
topic Cryptography and Security
url https://arxiv.org/abs/2508.10327