Escape method of malicious traffic based on backdoor attack

Launching backdoor attacks against deep learning (DL)-based network traffic classifiers, and a method of malicious traffic escape was proposed based on the backdoor attack. Backdoors were embedded in classifiers by mixing poisoned training samples with clean samples during the training process. Thes...

Full description

Saved in:
Bibliographic Details
Main Authors: MA Bowen, GUO Yuanbo, MA Jun, ZHANG Qi, FANG Chen
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2024-04-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024077/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841539197023813632
author MA Bowen
GUO Yuanbo
MA Jun
ZHANG Qi
FANG Chen
author_facet MA Bowen
GUO Yuanbo
MA Jun
ZHANG Qi
FANG Chen
author_sort MA Bowen
collection DOAJ
description Launching backdoor attacks against deep learning (DL)-based network traffic classifiers, and a method of malicious traffic escape was proposed based on the backdoor attack. Backdoors were embedded in classifiers by mixing poisoned training samples with clean samples during the training process. These backdoor classifiers then identified the malicious traffic with an attacker-specific backdoor trigger as benign, allowing the malicious traffic to escape. Additionally, backdoor classifiers behaved normally on clean samples, ensuring the backdoor's concealment. Different backdoor triggers were adopted to generate various backdoor models, the effects of different malicious traffic on different backdoor models were compared, and the influence of different backdoors on the model's performance was analyzed. The effectiveness of the proposed method was verified through experiments, providing a new approach for escaping malicious traffic from classifiers.
format Article
id doaj-art-5f7377671faf43b5bf8f6171ac017e0a
institution Kabale University
issn 1000-436X
language zho
publishDate 2024-04-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-5f7377671faf43b5bf8f6171ac017e0a2025-01-14T07:24:11ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-04-0145738359254674Escape method of malicious traffic based on backdoor attackMA BowenGUO YuanboMA JunZHANG QiFANG ChenLaunching backdoor attacks against deep learning (DL)-based network traffic classifiers, and a method of malicious traffic escape was proposed based on the backdoor attack. Backdoors were embedded in classifiers by mixing poisoned training samples with clean samples during the training process. These backdoor classifiers then identified the malicious traffic with an attacker-specific backdoor trigger as benign, allowing the malicious traffic to escape. Additionally, backdoor classifiers behaved normally on clean samples, ensuring the backdoor's concealment. Different backdoor triggers were adopted to generate various backdoor models, the effects of different malicious traffic on different backdoor models were compared, and the influence of different backdoors on the model's performance was analyzed. The effectiveness of the proposed method was verified through experiments, providing a new approach for escaping malicious traffic from classifiers.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024077/backdoor attackescape of malicious trafficdeep learningnetwork traffic classification
spellingShingle MA Bowen
GUO Yuanbo
MA Jun
ZHANG Qi
FANG Chen
Escape method of malicious traffic based on backdoor attack
Tongxin xuebao
backdoor attack
escape of malicious traffic
deep learning
network traffic classification
title Escape method of malicious traffic based on backdoor attack
title_full Escape method of malicious traffic based on backdoor attack
title_fullStr Escape method of malicious traffic based on backdoor attack
title_full_unstemmed Escape method of malicious traffic based on backdoor attack
title_short Escape method of malicious traffic based on backdoor attack
title_sort escape method of malicious traffic based on backdoor attack
topic backdoor attack
escape of malicious traffic
deep learning
network traffic classification
url http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024077/
work_keys_str_mv AT mabowen escapemethodofmalicioustrafficbasedonbackdoorattack
AT guoyuanbo escapemethodofmalicioustrafficbasedonbackdoorattack
AT majun escapemethodofmalicioustrafficbasedonbackdoorattack
AT zhangqi escapemethodofmalicioustrafficbasedonbackdoorattack
AT fangchen escapemethodofmalicioustrafficbasedonbackdoorattack