{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T20:38:49Z","timestamp":1770755929819,"version":"3.50.0"},"reference-count":38,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T00:00:00Z","timestamp":1770681600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Project of State Key Laboratory of Synthetical Automation for Process Industrie","award":["SAPI-2025-KFKT-06"],"award-info":[{"award-number":["SAPI-2025-KFKT-06"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Adversarial examples are crucial tools for assessing the robustness of deep neural networks (DNNs) and revealing potential security vulnerabilities. Adversarial example generation methods based on Generative Adversarial Networks (GANs) have made significant progress in generating image adversarial examples, but still suffer from insufficient sparsity and transferability. To address these issues, this study proposes a novel semi-white-box untargeted adversarial example generation method named Wavelet-AdvGAN, with an explicit threat model defined as follows. Specifically, the attack is strictly untargeted without predefined target categories, aiming solely to mislead DNNs into classifying adversarial examples into any category other than the original label. It adopts a semi-white-box setting where attackers are denied access to the target model\u2019s private information. Regarding the generator\u2019s information dependence, the training phase only utilizes public resources (i.e., the target model\u2019s public architecture and CIFAR-10 public training data), while the test phase generates adversarial examples through one-step feedforward of clean images without interacting with the target model. The method incorporates a Frequency Sub-band Difference (FSD) module and a Wavelet Transform Local Feature (WTLF) extraction module, evaluating the differences between original and adversarial examples from the frequency domain perspective. This approach constrains the magnitude of perturbations, reinforces feature regions, and further enhances the attack effectiveness, thereby improving the sparsity and transferability of adversarial examples. Experimental results demonstrate that the Wavelet-AdvGAN method achieves an average increase of 1.26% in attack success rates under two defense strategies\u2014data augmentation and adversarial training. Additionally, the adversarial transferability improves by an average of 2.7%. Moreover, the proposed method exhibits a lower l0 norm, indicating better perturbation sparsity. Consequently, it effectively evaluates the robustness of deep neural networks.<\/jats:p>","DOI":"10.3390\/info17020182","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:10:52Z","timestamp":1770743452000},"page":"182","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Example Generation Method Based on Wavelet Transform"],"prefix":"10.3390","volume":"17","author":[{"given":"Meng","family":"Bi","sequence":"first","affiliation":[{"name":"School of Software, Shenyang University of Technology, Shenyang 110000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguo","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Software, Shenyang University of Technology, Shenyang 110000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Bank of Xinjiang Co., Ltd., Tianshan District, Urumqi 830000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5224-7303","authenticated-orcid":false,"given":"Longxin","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Shenyang University of Technology, Shenyang 110000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software, Shenyang University of Technology, Shenyang 110000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiafeng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shenyang University of Technology, Shenyang 110000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Valente, J., Ant\u00f3nio, J., Mora, C., and Jardim, S. (2023). Developments in Image Processing Using Deep Learning and Reinforcement Learning. J. Imaging, 9.","DOI":"10.3390\/jimaging9100207"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2300313","DOI":"10.1002\/aisy.202300313","article-title":"PowerGAN: A Machine Learning Approach for Power Side-Channel Attack on Compute-in-Memory Accelerators","volume":"5","author":"Wang","year":"2023","journal-title":"Adv. Intell. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3691625","article-title":"Adversarial Attacks and Countermeasures on Image Classification-based Deep Learning Models in Autonomous Driving Systems: A Systematic Review","volume":"57","author":"Badjie","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5718","DOI":"10.1007\/s11263-024-02153-0","article-title":"Artificial immune system of secure face recognition against adversarial attacks","volume":"132","author":"Ren","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref_5","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2014). Intriguing properties of neural networks. arXiv."},{"key":"ref_6","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2015). Explaining and Harnessing Adversarial Examples. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., and Li, J. (2018). Boosting Adversarial Attacks with Momentum. arXiv.","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref_8","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (2019). Towards Deep Learning Models Resistant to Adversarial Attacks. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Carlini, N., and Wagner, D. (2017, January 22\u201326). Towards Evaluating the Robustness of Neural Networks. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.","DOI":"10.1109\/SP.2017.49"},{"key":"ref_10","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Xiao, C., Li, B., Zhu, J.Y., He, W., Liu, M., and Song, D. (2019). Generating Adversarial Examples with Adversarial Networks. arXiv.","DOI":"10.24963\/ijcai.2018\/543"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mangla, P., Jandial, S., Varshney, S., and Balasubramanian, V.N. (2019). AdvGAN++: Harnessing latent layers for adversary generation. arXiv.","DOI":"10.1109\/ICCVW.2019.00257"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Bai, T., Zhao, J., Zhu, J., Han, S., Chen, J., Li, B., and Kot, A. (2021). AI-GAN: Attack-Inspired Generation of Adversarial Examples. arXiv.","DOI":"10.1109\/ICIP42928.2021.9506278"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Chen, H., Wang, X., Zhang, J., Jin, Z., Choo, K.K.R., Shen, J., and Yuan, D. (2024). GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model. arXiv.","DOI":"10.1137\/1.9781611978032.81"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3745","DOI":"10.1109\/TIFS.2025.3553043","article-title":"Toward Model Resistant to Transferable Adversarial Examples via Trigger Activation","volume":"20","author":"Yu","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kong, C., Luo, A., Bao, P., Yu, Y., Li, H., Zheng, Z., Wang, S., and Kot, A.C. (2025). MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection. arXiv.","DOI":"10.1109\/TDSC.2025.3604443"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Casem, J., Golecruz, G.M., and Ostia, C. (2023, January 21\u201323). Brushless DC Motor Fault Classification Using Support Vector Machine Algorithm with Discrete Wavelet Transform Feature Extraction. Proceedings of the 2023 9th International Conference on Control, Automation and Robotics (ICCAR), Beijing, China.","DOI":"10.1109\/ICCAR57134.2023.10151735"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1109\/TUFFC.2023.3278494","article-title":"Genetic Algorithm-Wavelet Transform Feature Extraction for Data-Driven Acoustic Resonance Spectroscopy","volume":"70","author":"Greenhall","year":"2023","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e17954","DOI":"10.7717\/peerj.17954","article-title":"Rapid estimation of soil water content based on hyperspectral reflectance combined with continuous wavelet transform, feature extraction, and extreme learning machine","volume":"12","author":"Chen","year":"2024","journal-title":"PeerJ"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"165","DOI":"10.4103\/jmss.jmss_145_21","article-title":"Nonlinear feature extraction methods based on dual-tree complex wavelet transform subimages of brain magnetic resonance imaging for the classification of multiple diseases","volume":"13","author":"Bazdar","year":"2023","journal-title":"J. Med. Signals Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s11227-012-0790-x","article-title":"Algorithms and architectures for 2D discrete wavelet transform","volume":"62","author":"Shahbahrami","year":"2012","journal-title":"J. Supercomput."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Xu, W., and Wan, Y. (2024). ELA: Efficient Local Attention for Deep Convolutional Neural Networks. arXiv.","DOI":"10.1007\/s11554-025-01719-6"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021, January 20\u201325). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). CBAM: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wu, Y., and He, K. (2018). Group Normalization. arXiv.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"14878","DOI":"10.1109\/TNNLS.2023.3281872","article-title":"On the Effectiveness of Adversarial Training Against Backdoor Attacks","volume":"35","author":"Gao","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_29","unstructured":"Wu, B., Wei, S., Zhu, M., Zheng, M., Zhu, Z., Zhang, M., Chen, H., Yuan, D., Liu, L., and Liu, Q. (2023). Defenses in Adversarial Machine Learning: A Survey. arXiv."},{"key":"ref_30","unstructured":"Cheng, X., Fu, K., and Farnia, F. (2025). Stability and Generalization in Free Adversarial Training. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"100573","DOI":"10.1016\/j.cosrev.2023.100573","article-title":"Defense strategies for Adversarial Machine Learning: A survey","volume":"49","author":"Bountakas","year":"2023","journal-title":"Comput. Sci. Rev."},{"key":"ref_32","unstructured":"Li, L., and Spratling, M. (2023). Data Augmentation Alone Can Improve Adversarial Training. arXiv."},{"key":"ref_33","unstructured":"Luo, R., Wang, Y., and Wang, Y. (2023). Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning. arXiv."},{"key":"ref_34","unstructured":"Qin, C., Martens, J., Gowal, S., Krishnan, D., Dvijotham, K., Fawzi, A., De, S., Stanforth, R., and Kohli, P. (2019). Adversarial Robustness through Local Linearization. arXiv."},{"key":"ref_35","unstructured":"Rebuffi, S.A., Gowal, S., Calian, D.A., Stimberg, F., Wiles, O., and Mann, T. (2021). Data Augmentation Can Improve Robustness. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, L., Qiu, J., and Spratling, M. (2024). AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation. arXiv.","DOI":"10.1007\/s11263-024-02206-4"},{"key":"ref_37","unstructured":"Cuturi, M. (2013). Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances. arXiv."},{"key":"ref_38","unstructured":"Krizhevsky, A. (2026, February 03). Learning Multiple Layers of Features from Tiny Images. Available online: https:\/\/api.semanticscholar.org\/CorpusID:18268744."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/182\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:16:20Z","timestamp":1770743780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,10]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["info17020182"],"URL":"https:\/\/doi.org\/10.3390\/info17020182","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,10]]}}}