{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T10:49:33Z","timestamp":1769597373863,"version":"3.49.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Science and Technology on Information System Engineering Laboratory","award":["05202104"],"award-info":[{"award-number":["05202104"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806095"],"award-info":[{"award-number":["61806095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30920021130"],"award-info":[{"award-number":["30920021130"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Photos or videos taken by individuals often carry sensitive details such as facial identities, which has led to an escalating societal interest in privacy protection measures. We suggest an improved face identity transformer that offers password-protected anonymization and de-anonymization of photo-realistic facial images in visual data. Our face identity transformer is designed to (1) erase facial identity information after anonymization, (2) restore the original face when a correct password is provided and (3) generate an incorrect but realistic face when given an incorrect password. The processes of image anonymization and de-anonymization are facilitated through a password scheme, a multi-task learning objective and generative adversarial networks comprising InfoGAN and contrastive learning. In-depth experiments indicate that our methodology can execute anonymization and de-anonymization based on password conditions whilst reducing training time and enhancing image quality compared to existing anonymization procedures. Additionally, it maintains a recognition rate as low as 4.8% for anonymized images without sacrificing the face detection rate of the original method.<\/jats:p>","DOI":"10.1093\/comjnl\/bxad111","type":"journal-article","created":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T10:38:06Z","timestamp":1701513486000},"page":"1910-1919","source":"Crossref","is-referenced-by-count":1,"title":["Anonymization of face images with Contrastive Learning"],"prefix":"10.1093","volume":"67","author":[{"given":"Xintong","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology , 200 Xiaolingwei, Xuanwu District, Nanjing 210094 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Run","family":"Cui","sequence":"additional","affiliation":[{"name":"LG AI Research , Seoul 07336, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanying","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology , 200 Xiaolingwei, Xuanwu District, Nanjing 210094 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kedong","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology , 200 Xiaolingwei, Xuanwu District, Nanjing 210094 , China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"2024062312372988300_ref1","doi-asserted-by":"crossref","first-page":"5962","DOI":"10.1109\/TPAMI.2021.3087709","article-title":"ArcFace: additive angular margin loss for deep face recognition","volume":"44","author":"Deng","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2024062312372988300_ref2","first-page":"6738","article-title":"SphereFace: deep hypersphere embedding for face recognition","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326","author":"Liu","year":"2017"},{"key":"2024062312372988300_ref3","first-page":"235","article-title":"Privacy-preserving face recognition","volume-title":"Privacy Enhancing Technologies, 9th International Symposium, PETS 2009, Seattle, WA, USA, August 5\u20137. Proceedings, Lecture Notes in Computer Science","author":"Erkin","year":"2009"},{"key":"2024062312372988300_ref4","first-page":"27","article-title":"The privacy-utility tradeoff for remotely teleoperated robots","volume-title":"Proceedings of the Tenth Annual ACM\/IEEE International Conference on Human-Robot Interaction, HRI 2015, Portland, OR, USA, March 2\u20135","author":"Butler","year":"2015"},{"key":"2024062312372988300_ref5","first-page":"4255","article-title":"Privacy-preserving human activity recognition from extreme low resolution","volume-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4\u20139, San Francisco, California, USA","author":"Ryoo","year":"2017"},{"key":"2024062312372988300_ref6","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/TKDE.2005.32","article-title":"Preserving privacy by de-identifying face images","volume":"17","author":"Newton","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2024062312372988300_ref7","first-page":"1","article-title":"$\\mathrm{\\kappa} $-Same-net: neural-network-based face deidentification","volume-title":"International Conference and Workshop on Bioinspired Intelligence, IWOBI 2017, Funchal, Portugal, July 10\u201312","author":"Meden","year":"2017"},{"key":"2024062312372988300_ref8","first-page":"82","article-title":"Semi-adversarial networks: convolutional autoencoders for imparting privacy to face images","volume-title":"2018 International Conference on Biometrics, ICB 2018, Gold Coast, Australia, February 20\u201323","author":"Mirjalili","year":"2018"},{"key":"2024062312372988300_ref9","doi-asserted-by":"crossref","first-page":"9400","DOI":"10.1109\/TIP.2020.3024026","article-title":"PrivacyNet: semi-adversarial networks for multi-attribute face privacy","volume":"29","author":"Mirjalili","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"2024062312372988300_ref10","first-page":"56","article-title":"AnonymousNet: natural face de-identification with measurable privacy","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2019, Long Beach, CA, USA, June 16\u201320","author":"Li","year":"2019"},{"key":"2024062312372988300_ref11","first-page":"5446","article-title":"CIAGAN: conditional identity anonymization generative adversarial networks","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319","author":"Maximov","year":"2020"},{"key":"2024062312372988300_ref12","first-page":"565","article-title":"DeepPrivacy: a generative adversarial network for face anonymization","volume-title":"Advances in Visual Computing - 14th International Symposium on Visual Computing, ISVC 2019, Lake Tahoe, NV, USA, October 7\u20139, Proceedings, Part I, Lecture Notes in Computer Science","author":"Hukkel\u00e5s","year":"2019"},{"key":"2024062312372988300_ref13","article-title":"DP-Image: differential privacy for image data in feature space","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"2024062312372988300_ref14","first-page":"639","article-title":"Learning to anonymize faces for privacy preserving action detection","volume-title":"Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8\u201314, Proceedings, Part I, Lecture Notes in Computer Science","author":"Ren","year":"2018"},{"key":"2024062312372988300_ref15","first-page":"64","article-title":"imdpgan: Generating private and specific data with generative adversarial networks","volume-title":"Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, TPS-ISA 2020, Atlanta, GA, USA, October 28\u201331","author":"Gupta","year":"2020"},{"key":"2024062312372988300_ref16","first-page":"727","article-title":"Password-conditioned anonymization and deanonymization with face identity transformers","volume-title":"Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23\u201328, Proceedings, Part XXIII, Lecture Notes in Computer Science","author":"Gu","year":"2020"},{"key":"2024062312372988300_ref17","first-page":"784","article-title":"Practical image obfuscation with provable privacy","volume-title":"IEEE International Conference on Multimedia and Expo, ICME 2019, Shanghai, China, July 8\u201312","author":"Fan","year":"2019"},{"key":"2024062312372988300_ref18","doi-asserted-by":"crossref","first-page":"101951","DOI":"10.1016\/j.cose.2020.101951","article-title":"Privacy preserving face recognition utilizing differential privacy","volume":"97","author":"Chamikara","year":"2020","journal-title":"Comput. Secur."},{"key":"2024062312372988300_ref19","first-page":"1","article-title":"K-Same-Siamese-GAN: K-Same algorithm with generative adversarial network for facial image de-identification with hyperparameter tuning and mixed precision training","volume-title":"16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019, Taipei, Taiwan, September 18\u201321","author":"Pan","year":"2019"},{"key":"2024062312372988300_ref20","first-page":"148","article-title":"Image pixelization with differential privacy","volume-title":"Data and Applications Security and Privacy XXXII - 32nd Annual IFIP WG 11.3 Conference, DBSec 2018, Bergamo, Italy, July 16\u201318, Proceedings, Lecture Notes in Computer Science","author":"Fan","year":"2018"},{"key":"2024062312372988300_ref21","first-page":"656","article-title":"Certified robustness to adversarial examples with differential privacy","volume-title":"2019 IEEE Symposium on Security and Privacy, SP 2019, San Francisco, CA, USA, May 19\u201323","author":"L\u00e9cuyer","year":"2019"},{"key":"2024062312372988300_ref22","first-page":"abs\/2005.00783","article-title":"Differentially private generation of small images","author":"Schwabedal","year":"2020","journal-title":"CoRR"},{"key":"2024062312372988300_ref23","first-page":"7315","article-title":"Extreme low resolution activity recognition with multi-siamese embedding learning","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137","author":"Ryoo","year":"2018"},{"key":"2024062312372988300_ref24","first-page":"5050","article-title":"Natural and effective obfuscation by head inpainting","volume-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18\u201322","author":"Sun","year":"2018"},{"key":"2024062312372988300_ref25","first-page":"2172","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5\u201310","author":"Chen","year":"2016"},{"key":"2024062312372988300_ref26","first-page":"2242","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","volume-title":"IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22\u201329","author":"Zhu","year":"2017"},{"key":"2024062312372988300_ref27","first-page":"5967","article-title":"Image-to-image translation with conditional adversarial networks","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326","author":"Isola","year":"2017"},{"key":"2024062312372988300_ref28","first-page":"319","article-title":"Contrastive learning for unpaired image-to-image translation","volume-title":"Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23\u201328, Proceedings, Part IX, Lecture Notes in Computer Science","author":"Park","year":"2020"},{"key":"2024062312372988300_ref29","doi-asserted-by":"crossref","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","article-title":"A style-based generator architecture for generative adversarial networks","volume":"43","author":"Karras","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2024062312372988300_ref30","first-page":"465","article-title":"Toward multimodal image-to-image translation","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139","author":"Zhu","year":"2017"},{"key":"2024062312372988300_ref31","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July, Virtual Event, Proceedings of Machine Learning Research","author":"Chen","year":"2020"},{"key":"2024062312372988300_ref32"},{"key":"2024062312372988300_ref33","first-page":"abs\/1411.7923","article-title":"Learning face representation from scratch","author":"Yi","year":"2014","journal-title":"CoRR"},{"key":"2024062312372988300_ref34","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint face detection and alignment using multitask cascaded convolutional networks","volume":"23","author":"Zhang","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"2024062312372988300_ref35","first-page":"343","article-title":"Gan-leaks: A taxonomy of membership inference attacks against generative models","volume-title":"CCS \u201820: 2020 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, USA, November 9\u201313","author":"Chen","year":"2020"},{"key":"2024062312372988300_ref36","first-page":"2813","article-title":"Least squares generative adversarial networks","volume-title":"IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22\u201329","author":"Mao","year":"2017"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/5\/1910\/58308128\/bxad111.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/5\/1910\/58308128\/bxad111.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T12:39:26Z","timestamp":1719146366000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/67\/5\/1910\/7456152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":36,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,11,30]]},"published-print":{"date-parts":[[2024,6,22]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxad111","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,5]]},"published":{"date-parts":[[2023,11,30]]}}}