CETP: A novel semi-supervised framework based on contrastive pre-training for imbalanced encrypted traffic classification

计算机科学 培训(气象学) 加密 人工智能 机器学习 计算机安全 气象学 物理
作者
Xinjie Lin,Longtao He,Gaopeng Gou,Jing Yu,Zhong Guan,Xiang Li,Juncheng Guo,Gang Xiong
出处
期刊:Computers & Security [Elsevier BV]
卷期号:143: 103892-103892 被引量:33
标识
DOI:10.1016/j.cose.2024.103892
摘要

Encrypted traffic classification (ETC) requires differentiated and robust traffic representation captured from content-agnostic and imbalanced traffic data for accurate classification, which is challenging but indispensable for enabling network security and network management. Some existing deep-learning based ETC approaches have achieved promising results, but have limitations in real-world network environments: 1) label bias caused by traffic class imbalance and 2) traffic homogeneity due to component sharing. How to leverage open-domain unlabeled imbalanced traffic data to learn representation with strong generalization ability remains a key challenge. In this paper, we propose a novel imbalanced traffic representation model, called Contrastive Encrypted Traffic Pre-training (CETP), which pre-trains deep multi-granularity traffic representation from imbalanced data without directly using application labels. The pre-trained model can be further mitigated against label bias due to imbalance by semi-supervised continual fine-tuning via pseudo-label iterations and dynamic loss-weighting algorithms. CETP achieves state-of-the-art performance across four imbalanced encrypted traffic classification tasks, remarkably improving the F1 to 96.31% (2.74%↑) for CP-Android, 93.86% (3.58%↑) for CIC-2019, and 84.16% (10.19%↑) for ISCX-VPN. Meanwhile, we further validate the effectiveness of CETP in QUIC-based imbalanced encrypted traffic. Notably, we verify through analytical experiments that CETP not only effectively relieves label bias and homogeneous flow misclassification, but also extends to ETC methods with diverse feature extractors.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
风吹麦浪的应助被热情的远锋采纳,获得10
1秒前
老豆完成签到,获得积分10
1秒前
大富婆发布了新的文献求助10
2秒前
张强发布了新的文献求助10
2秒前
3秒前
3秒前
隐形曼青的应助被111采纳,获得10
3秒前
4秒前
老豆发布了新的文献求助10
4秒前
5秒前
我是老大的应助被鸢尾采纳,获得10
6秒前
周周完成签到,获得积分10
8秒前
8秒前
q额完成签到,获得积分20
9秒前
9秒前
alan发布了新的文献求助10
9秒前
小y同学发布了新的文献求助10
9秒前
maolei69完成签到,获得积分10
10秒前
123发布了新的文献求助10
11秒前
master发布了新的文献求助30
11秒前
情怀的应助被tlc_191026采纳,获得30
12秒前
12秒前
lzh关闭了lzh的文献求助
13秒前
qiuhai发布了新的文献求助10
13秒前
13秒前
星辰大海的应助被风格的好的采纳,获得10
14秒前
15秒前
任江归完成签到,获得积分10
16秒前
零负一的应助被周周周采纳,获得10
16秒前
fb1993关注了科研通微信公众号
16秒前
bluemoon发布了新的文献求助10
17秒前
17秒前
18秒前
123564的应助被corleeang采纳,获得10
18秒前
18秒前
易128_完成签到,获得积分10
20秒前
qiuhai完成签到,获得积分10
21秒前
赘婿的应助被李哈哈采纳,获得10
22秒前
高大的千秋完成签到,获得积分10
23秒前
辛夷完成签到 ,获得积分10
24秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183414
求助须知:如何正确求助?哪些是违规求助? 9572730
关于积分的说明 21827174
捐赠科研通 7780508
什么是DOI,文献DOI怎么找? 3434008
关于科研通互助平台的介绍 2558183
邀请新用户注册赠送积分活动 2480343