Multi-task adversarial attribution method based on hierarchical structure

Deep neural networks have demonstrated superior performance in various computer vision tasks. However, they have been found to be highly susceptible to adversarial attacks, which involve the addition of perturbations to examples during the inference phase that are imperceptible to the human eye. To...

Full description

Saved in:
Bibliographic Details
Main Authors: SUN Xu, ZHANG Wenqiong, LONG Xianzhong, LI Yun
Format: Article
Language:English
Published: POSTS&TELECOM PRESS Co., LTD 2025-02-01
Series:网络与信息安全学报
Subjects:
Online Access:http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390458191478784
author SUN Xu
ZHANG Wenqiong
LONG Xianzhong
LI Yun
author_facet SUN Xu
ZHANG Wenqiong
LONG Xianzhong
LI Yun
author_sort SUN Xu
collection DOAJ
description Deep neural networks have demonstrated superior performance in various computer vision tasks. However, they have been found to be highly susceptible to adversarial attacks, which involve the addition of perturbations to examples during the inference phase that are imperceptible to the human eye. To defend against adversarial attacks, some works have explored the reverse engineering of adversarial examples, known as the adversarial attribution problem. By attributing the attack algorithm and victim model used to generate adversarial examples, defenders can gain insights into the attacker’s knowledge and targets, thereby enabling the design of more effective defense algorithms against corresponding attacks. Existing methods have mostly approached the adversarial attribution problem as a single-task learning problem. However, as the scope of attack algorithms and victim models has expanded, single-task learning has faced the challenge of combinatorial explosion. To improve the accuracy of adversarial attribution and meet the requirements for different attribution granularities, attack algorithms and victim models were layered, and the dependencies between different levels were utilized. A multi-task adversarial attribution method based on a hierarchical structure was proposed. This method simultaneously performed the attribution tasks of attack algorithms and victim models at different levels and employed hierarchical path prediction to learn the dependencies between these levels. Experimental results on multiple datasets demonstrate that the proposed method achieves better attribution performance compared to other attribution methods.
format Article
id doaj-art-43dc3efbf88a4224813d7a28e6dc1cf3
institution Kabale University
issn 2096-109X
language English
publishDate 2025-02-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 网络与信息安全学报
spelling doaj-art-43dc3efbf88a4224813d7a28e6dc1cf32025-08-20T03:41:39ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2025-02-01119210586731996Multi-task adversarial attribution method based on hierarchical structureSUN XuZHANG WenqiongLONG XianzhongLI YunDeep neural networks have demonstrated superior performance in various computer vision tasks. However, they have been found to be highly susceptible to adversarial attacks, which involve the addition of perturbations to examples during the inference phase that are imperceptible to the human eye. To defend against adversarial attacks, some works have explored the reverse engineering of adversarial examples, known as the adversarial attribution problem. By attributing the attack algorithm and victim model used to generate adversarial examples, defenders can gain insights into the attacker’s knowledge and targets, thereby enabling the design of more effective defense algorithms against corresponding attacks. Existing methods have mostly approached the adversarial attribution problem as a single-task learning problem. However, as the scope of attack algorithms and victim models has expanded, single-task learning has faced the challenge of combinatorial explosion. To improve the accuracy of adversarial attribution and meet the requirements for different attribution granularities, attack algorithms and victim models were layered, and the dependencies between different levels were utilized. A multi-task adversarial attribution method based on a hierarchical structure was proposed. This method simultaneously performed the attribution tasks of attack algorithms and victim models at different levels and employed hierarchical path prediction to learn the dependencies between these levels. Experimental results on multiple datasets demonstrate that the proposed method achieves better attribution performance compared to other attribution methods.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025009deep learningadversarial attributionmulti-task learninghierarchical structure
spellingShingle SUN Xu
ZHANG Wenqiong
LONG Xianzhong
LI Yun
Multi-task adversarial attribution method based on hierarchical structure
网络与信息安全学报
deep learning
adversarial attribution
multi-task learning
hierarchical structure
title Multi-task adversarial attribution method based on hierarchical structure
title_full Multi-task adversarial attribution method based on hierarchical structure
title_fullStr Multi-task adversarial attribution method based on hierarchical structure
title_full_unstemmed Multi-task adversarial attribution method based on hierarchical structure
title_short Multi-task adversarial attribution method based on hierarchical structure
title_sort multi task adversarial attribution method based on hierarchical structure
topic deep learning
adversarial attribution
multi-task learning
hierarchical structure
url http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025009
work_keys_str_mv AT sunxu multitaskadversarialattributionmethodbasedonhierarchicalstructure
AT zhangwenqiong multitaskadversarialattributionmethodbasedonhierarchicalstructure
AT longxianzhong multitaskadversarialattributionmethodbasedonhierarchicalstructure
AT liyun multitaskadversarialattributionmethodbasedonhierarchicalstructure