电子学报2026，Vol.54Issue(1)：125-140,16.DOI:10.12263/DZXB.20250521
基于空频双域特征融合的高迁移性对抗样本生成方法
A Highly Transferable Adversarial Example Generation Method via Spatial-Frequency Dual-Domain Feature Fusion
摘要
Abstract
Despite the remarkable performance of deep neural networks across various fields,the existence of adver-sarial examples reveals significant security vulnerabilities.Existing black-box attack methods typically operate within a sin-gle domain,overlooking the importance of multi-domain feature co-perturbation in enhancing the transferability of adversar-ial examples.Moreover,many methods suffer from a single-purpose loss function,making it difficult to balance target class guidance and gradient stability.To address these issues,this paper proposes a high-transferability adversarial examples gen-eration method based on spatial-frequency dual-domain feature fusion(SFDFF).Specifically,the input examples are first transformed from the spatial domain to the frequency domain using the discrete cosine transform,and region-level feature fusion is performed between the input and clean examples in the frequency domain.Then,the input examples are restored to the spatial domain via the inverse discrete cosine transform,and noise based on the statistical characteristics of the original examples are injected.Next,channel-level fusion of spatial features between the input and clean examples are conducted.Fi-nally,a dual-guidance loss function is designed to simultaneously enhance target class directionality and gradient stability.Extensive experiments on ImageNet-Compatible and CIFAR-10 datasets demonstrate the performance of the proposed method.For instance,the attack success rate of the proposed SFDFF increases by 2.5%compared to the state-of-the-art method when transferred from the adv-RN-50 to LeViT model on ImageNet-Compatible dataset.The code is available at https://github.com/ipkpkpk/SFDFF.关键词
对抗样本/特征融合/频率域/空间域/黑盒攻击/迁移性Key words
adversarial examples/feature fusion/frequency domain/spatial domain/black-box attack/transferability分类
信息技术与安全科学引用本文复制引用
张世辉,赵鹏宇,张尧,韩少杰..基于空频双域特征融合的高迁移性对抗样本生成方法[J].电子学报,2026,54(1):125-140,16.基金项目
国家自然科学基金(No.62476235) （No.62476235）
河北省自然科学基金(No.F2023203012) National Natural Science Foundation of China(No.62476235) （No.F2023203012）
Natural Science Foundation of Hebei Province(No.F2023203012) （No.F2023203012）
