{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:34Z","timestamp":1750309534447,"version":"3.41.0"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T00:00:00Z","timestamp":1741305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172153"],"award-info":[{"award-number":["62172153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Scientific Research Fund of Hunan Provincial Education Department","award":["22B0885"],"award-info":[{"award-number":["22B0885"]}]},{"name":"Hunan Provincial Key Research and Development Program of China","award":["2024AQ2032"],"award-info":[{"award-number":["2024AQ2032"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>In certain specific scenarios, there is a risk of privacy leakage in terms of the soft biometric attributes on a person\u2019s face. However, existing face privacy-enhancing techniques suffer from limited generalizability, meaning that they can only induce misclassification in a specific classifier but fail to generalize this effect well to arbitrary attribute classifiers. Moreover, existing methods reverse attributes to improve face privacy, but this may result in privacy recovery. To address those problems, we propose GFPNet, a novel privacy-enhancing model that can provide generalizable and reliable privacy to face images. The key factor for improving generalizability is that GFPNet uses defense training, which is an effective way to improve model robustness, to dynamically strengthen the mediocre auxiliary attribute classifier during iterative training. Specifically, the generalizability of GFPNet is enhanced in the game between attack and defense, where the generator attempts to deceive the auxiliary attribute classifier and the classifier defends against the generator\u2019s attack by defense training. Furthermore, instead of reversing attributes, skewing attributes to one side is used to avoid attribute recovery. GFPNet also integrates a face matcher, multi-scale discriminator, and Demiguise Attack to improve face matching and image quality. Extensive experiments demonstrate that GFPNet has excellent generalizability to arbitrary attribute classi\ufb01ers and satisfactory face-matching utility.<\/jats:p>","DOI":"10.1145\/3715132","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T15:53:42Z","timestamp":1738079622000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GFPNet: Generalizable Face Privacy Network with Dynamic Defense Training"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2579-1713","authenticated-orcid":false,"given":"Yucheng","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Electrical Engineering, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2774-3106","authenticated-orcid":false,"given":"Siwang","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electrical Engineering, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9642-4873","authenticated-orcid":false,"given":"Deyan","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hunan First Normal University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5464-3564","authenticated-orcid":false,"given":"Liubo","family":"Ouyang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electrical Engineering, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2732-2718","authenticated-orcid":false,"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electrical Engineering, Hunan University, Changsha, China"}]}],"member":"320","published-online":{"date-parts":[[2025,3,7]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"1","volume-title":"2020 International Conference of the Biometrics Special Interest Group (BIOSIG)","author":"Alonso-Fernandez Fernando","year":"2020","unstructured":"Fernando Alonso-Fernandez, Kevin Hernandez Diaz, Silvia Ramis, Francisco J. Perales, and Josef Bigun. 2020. Soft-biometrics estimation in the era of facial masks. In 2020 International Conference of the Biometrics Special Interest Group (BIOSIG). IEEE, 1\u20136."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/591"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/95"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304415.3304509"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_1_9_2","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in Neural Information Processing Systems 27 (2014), 2672\u20132680.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_10_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Goodfellow Ian","year":"2015","unstructured":"Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In International Conference on Learning Representations, 1\u201311."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_1_15_2","first-page":"1","volume-title":"7th International Symposium on Digital Forensics and Security (ISDFS)","author":"Sami Jaha Emad","year":"2019","unstructured":"Emad Sami Jaha. 2019. Augmenting gabor-based face recognition with global soft biometrics. In 7th International Symposium on Digital Forensics and Security (ISDFS), 1\u20135."},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Catherine Jasserand. 2019. Reprocessing of biometric data for law enforcement purposes: Individuals\u2019 safeguards caught at the interface between the GDPR and the \u2018Police\u2019 directive? Ph.D. dissertation University of Groningen Holland.","DOI":"10.2139\/ssrn.4298545"},{"key":"e_1_3_1_17_2","volume-title":"3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations."},{"key":"e_1_3_1_18_2","volume-title":"International Conference on Learning Representations","author":"Kurakin Alexey","year":"2017","unstructured":"Alexey Kurakin, Ian J. Goodfellow, and Samy Bengio. 2017. Adversarial machine learning at scale. In International Conference on Learning Representations."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_1_21_2","volume-title":"International Conference on Learning Representations","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00067"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3096024"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00036"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00023"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2018.8698605"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924619"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3024026"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3015420"},{"key":"e_1_3_1_30_2","first-page":"2642","volume-title":"International Conference on Machine Learning","author":"Odena Augustus","year":"2017","unstructured":"Augustus Odena, Christopher Olah, and Jonathon Shlens. 2017. Conditional image synthesis with auxiliary classifier gans. In International Conference on Machine Learning. PMLR, 2642\u20132651."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_1_32_2","first-page":"1","article-title":"PrivacyProber: Assessment and detection of soft\u2013biometric privacy\u2013enhancing techniques","author":"Rot Peter","year":"2023","unstructured":"Peter Rot, Klemen Grm, Peter Peer, and Vitomir \u0160truc. 2023. PrivacyProber: Assessment and detection of soft\u2013biometric privacy\u2013enhancing techniques. In IEEE Transactions on Dependable and Secure Computing, 1\u201318.","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2987694"},{"key":"e_1_3_1_34_2","first-page":"1","article-title":"Privacy-preserving image acquisition for neural vision systems","author":"Sepehri Yamin","year":"2022","unstructured":"Yamin Sepehri, Pedram Pad, Cl\u00e9ment K\u00fcndig, Pascal Frossard, and L. Andrea Dunbar. 2022. Privacy-preserving image acquisition for neural vision systems. IEEE Transactions on Multimedia, 1\u201312.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_1_35_2","unstructured":"Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna Dumitru Erhan Ian Goodfellow and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv:1312.6199. Retrieved from https:\/\/arxiv.org\/abs\/1312.6199"},{"key":"e_1_3_1_36_2","first-page":"6105","volume-title":"International Conference on Machine Learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, 6105\u20136114."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3155878"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3381088"},{"key":"e_1_3_1_39_2","unstructured":"Florian Tram\u00e8r Alexey Kurakin Nicolas Papernot Ian Goodfellow Dan Boneh and Patrick McDaniel. 2017. Ensemble adversarial training: Attacks and defenses. arXiv:1705.07204. Retrieved from https:\/\/arxiv.org\/abs\/1705.07204"},{"key":"e_1_3_1_40_2","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten Laurens","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (2008), 11.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWBF50991.2021.9465088"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_3_1_44_2","first-page":"63","volume-title":"European Conference on Computer Vision (ECCV) Workshops","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. 2018. Esrgan: Enhanced super-resolution generative adversarial networks. In European Conference on Computer Vision (ECCV) Workshops, 63\u201379."},{"key":"e_1_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Yang Wang Bo Dong Ke Xu Haiyin Piao Yufei Ding Baocai Yin and Xin Yang. 2023. A geometrical approach to evaluate the adversarial robustness of deep neural networks. 19 (2023) 5s.","DOI":"10.1145\/3587936"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/430"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00475"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2018.8361338"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304222.3304312"},{"key":"e_1_3_1_50_2","article-title":"Multimodal soft biometrics: Combining ear and face biometrics for age and gender classification","author":"Yaman Dogucan","year":"2021","unstructured":"Dogucan Yaman, Fevziye Irem Eyiokur, and Haz\u0131m Kemal Ekenel. 2021. Multimodal soft biometrics: Combining ear and face biometrics for age and gender classification. Multimedia Tools and Applications (2021), 81 (2021), 22695\u201322713.","journal-title":"Multimedia Tools and Applications (2021)"},{"key":"e_1_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Chenggang Yan Lixuan Meng Liang Li Jiehua Zhang Zhan Wang Jian Yin Jiyong Zhang Yaoqi Sun and Bolun Zheng. 2022. Age-invariant face recognition by multi-feature fusion and decomposition with self-attention. 18 1s (2022).","DOI":"10.1145\/3472810"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142952"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3014561"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715132","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:18Z","timestamp":1750295898000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,7]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3715132"],"URL":"https:\/\/doi.org\/10.1145\/3715132","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,3,7]]},"assertion":[{"value":"2024-01-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}