To address the problems of poor attack performance and low authenticity of adversarial examples caused by the perturbations generated by the adversarial example generation method based on generative adversarial networks (AdvGAN) deviating from key image regions and lacking controllability, a Diff-AdvGAN adversarial example generation method was proposed. Firstly, an Adaptively Spatial Feature Fusion (ASFF) module was employed to fuse featusare maps of the images at different scales. Then, the fused feature maps werere input into a generator to produce perturbations, and a Stochastic Differential Guide Module (SDGM) was used to enhance the controllability of the perturbations and generate adversarial examples. Finally, the adversarial examples are fed into a discriminator and a target model, the loss values were iteratively calculated and fed back to the generator to generate stronger perturbations with improved attack performance. Experimental results show that the Diff-AdvGAN method achieves attack success rates of over 99% on the MNIST dataset for the LeNet C, VGG11, and C&W models, and attack success rates of 96.17% and 95.82% for the ResNet18 and ResNet32 models on the CIFAR-10 dataset. Moreover, the perturbations generated by this method can accurately locate in the critical regions of the images, exhibiting high sparsity and small magnitudes, demonstrating significant advantages compared to comparison method.
KimI, BaekW, KimS. Spatially attentive output layer for image classification[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA, 2020: 9533-9542.
[2]
BoutrosF, DamerN, KirchbuchnerF, et al. Elasticface: Elastic margin loss for deep face recognition[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022: 1578-1587.
[3]
HauslerS, GargS, XuM, et al. Patch-netvlad: Multi-scale fusion of locally-global descriptors for place recognition[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA, 2021: 14141-14152.
[4]
SzegedyC, ZarembaW, SutskeverI, et al. Intriguing properties of neural networks[C]∥2nd International Conference on Learning Representations, Banff, AB, Canada, 2014: 23-41.
JiShun-hui, HuLi-ming, ZhangPeng-cheng, et al. Adversarial example generation method based on sparse perturbation[J]. Journal of Software, 2023, 34(9): 4003-4017.
[7]
GoodfellowI J, ShlensJ, SzegedyC. Explaining and harnessing adversarial examples[J/OL]. [2025-05-01].
[8]
KurakinA, GoodfellowI J, BengioS. Adversarial examples in the physical world[C]∥5th International Conference on Learning Representations, Toulon, France, 2017: 1-14.
[9]
CarliniN, WagnerD. Towards evaluating the robustness of neural networks[C]∥2017 IEEE Symposium on Security and Privacy, San Jose, CA, USA, 2017: 39-57.
ZhaoZ L, DuaD, SinghS. Generating natural adversarial examples[C]∥6th International Conference on Learning Representations, Vancouver, BC, Canada, 2018: 1-15.
[12]
ArjovskyM, ChintalaS, BottouL. Wasserstein generative adversarial networks[C]∥Proceedings of the 34th International Conference on Machine Learning, Sydney, NSW, Australia:, 2017: 214-223.
[13]
ZhangW J. Generating adversarial examples in one shot with image-to-image translation GAN[J]. IEEE Access, 2019, 7: 151103-151119.
[14]
XiaoC W, LiB, ZhuJ Y, et al. Generating adversarial examples with adversarial networks[C]∥Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 2018: 3905-3911.
HuangShuai-na, LiYu-xiang, MaoYue-heng, et al. Black-box transferable adversarial attacks based on ensemble advGAN[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(10): 2391-2398.
LiuYue-wen, SunZi-wen. Intrusion detection model based on generative adversarial networks in IWSN against adversarial attacks[J]. Journal of Jiangsu University (Natural Science Edition), 2025, 46(5): 562-569.
[19]
JandialS, ManglaP, VarshneyS, et al. AdvGAN++: harnessing latent layers for adversary generation[C]∥2019 IEEE/CVF International Conference on Computer Vision Workshop, Los Alamitos, CA, USA, 2019: 2045-2048.
[20]
SinghJ, GouldS, ZhengL. High-fidelity guided image synthesis with latent diffusion models[C]∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 2023: 5997-6006.
[21]
PodellD, EnglishZ, LaceyK, et al. SDXL: improving latent diffusion models for high-resolution image synthesis[J/OL]. [2024-05-03].
ChenX Q, GaoX T, ZhaoJ J, et al. Advdiffuser: Natural adversarial example synthesis with diffusion models[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France, 2023: 4562-4572.
[24]
LiuD C, WangX J, PengC L, et al. Adv-diffusion: Imperceptible adversarial face identity attack via latent diffusion model[C]∥Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(4): 3585-3593.
[25]
LiuS T, HuangD, WangY H. Learning spatial fusion for single-shot object detection[J/OL]. [2024-05-03].
[26]
HoJ, JainA, AbbeelP. Denoising diffusion probabilistic models[J]. Advances in neural information processing systems, 2020, 33: 6840-6851.
[27]
SongJ M, MengC L, ErmonS. Denoising diffusion implicit models[J/OL]. [2024-05-03].
[28]
TramèrF, KurakinA, PapernotN, et al. Ensemble adversarial training: attacks and defenses[C]∥6th International Conference on Learning Representations, Vancouver, BC, Canada, 2018: 1-20.
[29]
MadryA, MakelovA, SchmidtL, et al. Towards deep learning models resistant to adversarial attacks[C]∥6th International Conference on Learning Representations, Vancouver, BC, Canada, 2018: 1-23.