Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning

As the prevalence of facial recognition technology continued to grow, concerns about personal privacy breaches were also gradually intensifying. Despite recent studies attempting to safeguard photo privacy by generating adversarial examples to prevent unauthorized facial recognition systems from ide...

Full description

Saved in:
Bibliographic Details
Main Authors: CAI Jun, HUANG Tianqiang, ZHENG Aokun, YE Feng, XU Chao
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.2025001
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850057626315915264
author CAI Jun
HUANG Tianqiang
ZHENG Aokun
YE Feng
XU Chao
author_facet CAI Jun
HUANG Tianqiang
ZHENG Aokun
YE Feng
XU Chao
author_sort CAI Jun
collection DOAJ
description As the prevalence of facial recognition technology continued to grow, concerns about personal privacy breaches were also gradually intensifying. Despite recent studies attempting to safeguard photo privacy by generating adversarial examples to prevent unauthorized facial recognition systems from identifying individuals, these methods were often constrained by low attack success rates and weak transferability. To address this issue, a facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning was proposed. This algorithm initially devised a multiscale frequency decomposition module that meticulously partitioned the target facial image into frequency bands comprising distinct components. This module integrated frequency information with spatial information, thereby enabling the extraction of comprehensive information from the target facial image. Subsequently, a cycle-consistent generative adversarial networks (CycleGAN)-based adversarial attack algorithm with makeup transfer as its core was constructed. This algorithm employed a source facial image to generate high-quality makeup. During this process, a meta-learning attack module was introduced to calculate the loss function and update parameters. The meta-learning attack module enabled precise makeup processing, by which the target face's features were embedded into the makeup to create adversarial makeup images. This enabled the targeted attacks that were the focus of this study. The meta-learning attack module addressed the overfitting and generalization issues present in previous white-box model ensemble attacks, thereby enhancing the efficacy and generalization ability of the generated adversarial examples. The results of experimental analysis of different attack strategies demonstrate that the combination of multiscale frequency decomposition and meta-learning significantly enhances the success rate and robustness of attacks on facial recognition systems.
format Article
id doaj-art-4b78c181c52c4bcea21062028271aaca
institution DOAJ
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-4b78c181c52c4bcea21062028271aaca2025-08-20T02:51:23ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2025-02-011112914086732098Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learningCAI JunHUANG TianqiangZHENG AokunYE FengXU ChaoAs the prevalence of facial recognition technology continued to grow, concerns about personal privacy breaches were also gradually intensifying. Despite recent studies attempting to safeguard photo privacy by generating adversarial examples to prevent unauthorized facial recognition systems from identifying individuals, these methods were often constrained by low attack success rates and weak transferability. To address this issue, a facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning was proposed. This algorithm initially devised a multiscale frequency decomposition module that meticulously partitioned the target facial image into frequency bands comprising distinct components. This module integrated frequency information with spatial information, thereby enabling the extraction of comprehensive information from the target facial image. Subsequently, a cycle-consistent generative adversarial networks (CycleGAN)-based adversarial attack algorithm with makeup transfer as its core was constructed. This algorithm employed a source facial image to generate high-quality makeup. During this process, a meta-learning attack module was introduced to calculate the loss function and update parameters. The meta-learning attack module enabled precise makeup processing, by which the target face's features were embedded into the makeup to create adversarial makeup images. This enabled the targeted attacks that were the focus of this study. The meta-learning attack module addressed the overfitting and generalization issues present in previous white-box model ensemble attacks, thereby enhancing the efficacy and generalization ability of the generated adversarial examples. The results of experimental analysis of different attack strategies demonstrate that the combination of multiscale frequency decomposition and meta-learning significantly enhances the success rate and robustness of attacks on facial recognition systems.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025001facial recognition targeted attack algorithmmultiscale frequency decompositionCycleGANmeta-learning
spellingShingle CAI Jun
HUANG Tianqiang
ZHENG Aokun
YE Feng
XU Chao
Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning
网络与信息安全学报
facial recognition targeted attack algorithm
multiscale frequency decomposition
CycleGAN
meta-learning
title Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning
title_full Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning
title_fullStr Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning
title_full_unstemmed Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning
title_short Facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta-learning
title_sort facial recognition targeted attack algorithm based on multiscale frequency decomposition and meta learning
topic facial recognition targeted attack algorithm
multiscale frequency decomposition
CycleGAN
meta-learning
url http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025001
work_keys_str_mv AT caijun facialrecognitiontargetedattackalgorithmbasedonmultiscalefrequencydecompositionandmetalearning
AT huangtianqiang facialrecognitiontargetedattackalgorithmbasedonmultiscalefrequencydecompositionandmetalearning
AT zhengaokun facialrecognitiontargetedattackalgorithmbasedonmultiscalefrequencydecompositionandmetalearning
AT yefeng facialrecognitiontargetedattackalgorithmbasedonmultiscalefrequencydecompositionandmetalearning
AT xuchao facialrecognitiontargetedattackalgorithmbasedonmultiscalefrequencydecompositionandmetalearning