{"type":"ScholarlyArticle","title":"Anonymizing k Facial Attributes via Adversarial Perturbations","authors":[{"name":"Saheb Chhabra","slug":"saheb-chhabra","given":"Saheb","family":"Chhabra","affiliation":"IIIT Delhi , New Delhi , India"},{"name":"Richa Singh","slug":"richa-singh","given":"Richa","family":"Singh","affiliation":"IIIT Delhi , New Delhi , India"},{"name":"Mayank Vatsa","slug":"mayank-vatsa","given":"Mayank","family":"Vatsa","affiliation":"IIIT Delhi , New Delhi , India"},{"name":"Gaurav Gupta","slug":"gaurav-gupta","given":"Gaurav","family":"Gupta","affiliation":"Ministry of Electronics and Information Technology , New Delhi , India"}],"abstract":"A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age. Advancements in machine learning algorithms and popularity of sharing images on the World Wide Web, including social media websites, have increased the scope of data analytics and information profiling from photo collections. This poses a serious privacy threat for individuals who do not want to be profiled. This research presents a novel algorithm for anonymizing selective attributes which an individual does not want to share without affecting the visual quality of images. Using the proposed algorithm, a user can select single or multiple attributes to be surpassed while preserving identity information and visual content. The proposed adversarial perturbation based algorithm embeds imperceptible noise in an image such that attribute prediction algorithm for the selected attribute yields incorrect classification result, thereby preserving the information according to user's choice. Experiments on three popular databases i.e. MUCT, LFWcrop, and CelebA show that the proposed algorithm not only anonymizes \\textit{k}-attributes, but also preserves image quality and identity information.","doi":"10.24963/ijcai.2018/91","url":"https://ijcai.org/proceedings/2018/91","pdf":"https://ijcai.org/proceedings/2018/0091.pdf","markdown":"https://ijcai.org/proceedings/2018/91.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/91","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":91,"pages":{"first":656,"last":662},"keywords":["Computer Vision: Biometrics, Face and Gesture Recognition","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"],"videos":[],"references":[{"position":1,"raw":"[Abdulnabi et al., 2015] Abrar H Abdulnabi, Gang Wang, Ji- wen Lu, and Kui Jia. Multi-task cnn model for attribute prediction. IEEE TM, 17(11):1949-1959, 2015.","title":"Multi-task cnn model for attribute prediction","authors":"Gang Abrar H Abdulnabi, Jiwen Wang, Kui Lu, Jia","year":"2015","venue":"IEEE TM","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Amos et al., 2016] Brandon Amos, Bartosz Ludwiczuk, and Mahadev Satyanarayanan. Openface: A general- purpose face recognition library with mobile applications. Technical report, CMU-CS-16-118, 2016.","title":"Openface: A generalpurpose face recognition library with mobile applications","authors":"Brandon Amos, Bartosz Ludwiczuk, Mahadev Satyanarayanan","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Beveridge et al., 2013] J Ross Beveridge, P Jonathon Phillips, David S Bolme, Bruce A Draper, Geof H Givens, Yui Man Lui, Mohammad Nayeem Teli, Hao Zhang, W Todd Scruggs, Kevin W Bowyer, et al. The challenge of face recognition from digital point-and-shoot cameras. In IEEE BTAS, pages 1-8, 2013.","title":"The challenge of face recognition from digital point-and-shoot cameras","authors":"Ross Beveridge, Jonathon Phillips, David S Bolme, Bruce A Draper, Geof H Givens, Yui, Man Lui, Mohammad Nayeem Teli, Hao Zhang, Todd Scruggs, Kevin W Bowyer","year":"2013","venue":"IEEE BTAS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Boyle et al., 2000] Michael Boyle, Christopher Edwards, and Saul Greenberg. The effects of filtered video on aware- ness and privacy. In CSCW, pages 1-10. ACM, 2000.","title":"The effects of filtered video on awareness and privacy","authors":"Michael Boyle, Christopher Edwards, Saul Greenberg","year":"2000","venue":"CSCW","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carlini and Wagner, 2017] Nicholas Carlini and David Wagner. Towards evaluating the robustness of neural networks. In IEEE SP, pages 39-57, 2017.","title":"Towards evaluating the robustness of neural networks","authors":"Wagner Carlini, Nicholas Carlini, David Wagner","year":"2017","venue":"IEEE SP","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goswami et al., 2017] Gaurav Goswami, Mayank Vatsa, and Richa Singh. Face verification via learned representa- tion on feature-rich video frames. IEEE TIFS, 12(7):1686- 1698, 2017.","title":"Face verification via learned representation on feature-rich video frames","authors":"Gaurav Goswami, Mayank Vatsa, Richa Singh","year":"2017","venue":"IEEE TIFS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gross et al., 2006] Ralph Gross, Latanya Sweeney, Fer- nando De la Torre, and Simon Baker. Model-based face de-identification. In IEEE CVPRW, pages 161-161, 2006.","title":"Model-based face de-identification","authors":"Gross","year":"2006","venue":"IEEE CVPRW","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Huang et al., 2007] Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Mas- sachusetts, Amherst, October 2007.","title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","authors":"B Gary, Manu Huang, Tamara Ramesh, Erik Berg, Learned-Miller","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jourabloo et al., 2015] Amin Jourabloo, Xi Yin, and Xi- aoming Liu. Attribute preserved face de-identification. In IEEE ICB, 2015.","title":"Attribute preserved face de-identification","authors":"Amin Jourabloo, Xi Yin, Xiaoming Liu","year":"2015","venue":"IEEE ICB","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2016] Chao Li, Chao Xu, and Zhiyong Feng. Analysis of physiological for emotion recognition with the irs model. Neurocomputing, 178:103-111, 2016.","title":"Analysis of physiological for emotion recognition with the irs model","authors":"Chao Li, Chao Xu, Zhiyong Feng","year":"2016","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2015] Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In ICCV, 2015. [Milborrow et al., 2010] Stephen Milborrow, John Morkel, and Fred Nicolls. The MUCT Landmarked Face Database. PRASA, 2010. http://www.milbo.org/muct.","title":"Deep learning face attributes in the wild","authors":"Ziwei Liu, Ping Luo, Xiaogang Wang, Xiaoou Tang","year":"2010","venue":"The MUCT Landmarked Face Database","doi":null,"url":"http://www.milbo.org/muct","internal_url":null},{"position":12,"raw":"[Mirjalili and Ross, 2017] Vahid Mirjalili and Arun Ross. Soft biometric privacy: Retaining biometric utility of face images while perturbing gender. IEEE IJCB, 2017.","title":"Soft biometric privacy: Retaining biometric utility of face images while perturbing gender","authors":"Vahid Mirjalili, Arun Ross","year":"2017","venue":"IEEE IJCB","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mirjalili et al., 2017] Vahid Mirjalili, Sebastian Raschka, Anoop Namboodiri, and Arun Ross. Semi-adversarial net- works: Convolutional autoencoders for imparting privacy to face images. arXiv preprint arXiv:1712.00321, 2017.","title":"Semi-adversarial networks: Convolutional autoencoders for imparting privacy to face images","authors":"Vahid Mirjalili, Sebastian Raschka, Anoop Namboodiri, Arun Ross","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Newton et al., 2005] Elaine M Newton, Latanya Sweeney, and Bradley Malin. Preserving privacy by de-identifying face images. IEEE TKDE, 17(2):232-243, 2005.","title":"Preserving privacy by de-identifying face images","authors":"Latanya Elaine M Newton, Bradley Sweeney, Malin","year":"2005","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Othman and Ross, 2014] Asem A Othman and Arun Ross. Privacy of facial soft biometrics: Suppressing gender but retaining identity. In ECCV Workshops (2), pages 682- 696, 2014.","title":"Privacy of facial soft biometrics: Suppressing gender but retaining identity","authors":"A Asem, Arun Othman, Ross","year":"2014","venue":"ECCV Workshops","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Parkhi et al., 2015] Omkar M Parkhi, Andrea Vedaldi, An- drew Zisserman, et al. Deep face recognition. In BMVC, volume 1, page 6, 2015.","title":"Deep face recognition","authors":"Andrea Omkar M Parkhi, Andrew Vedaldi, Zisserman","year":"2015","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rozsa et al., 2016] Andras Rozsa, Manuel Günther, Ethan M Rudd, and Terrance E Boult. Are facial attributes adversarially robust? In IEEE ICPR, pages 3121-3127, 2016.","title":"Are facial attributes adversarially robust?","authors":"Andras Rozsa, Manuel Günther, Ethan M Rudd, Terrance E Boult","year":"2016","venue":"IEEE ICPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rozsa et al., 2017] Andras Rozsa, Manuel Günther, Ethan M Rudd, and Terrance E Boult. Facial at- tributes: Accuracy and adversarial robustness. PRL https://doi.org/10.1016/j.patrec.2017.10.024, 2017.","title":"Facial attributes: Accuracy and adversarial robustness","authors":"Andras Rozsa, Manuel Günther, Ethan M Rudd, Terrance E Boult","year":"2017","venue":"PRL","doi":"10.1016/j.patrec.2017.10.024","url":"https://doi.org/10.1016/j.patrec.2017.10.024","internal_url":null},{"position":19,"raw":"[Sethi et al., 2018] Akshay Sethi, Maneet Singh, Richa Singh, and Mayank Vatsa. Residual codean autoencoder for facial attribute analysis. PRL, 2018.","title":"Residual codean autoencoder for facial attribute analysis","authors":"Akshay Sethi, Maneet Singh, Richa Singh, Mayank Vatsa","year":"2018","venue":"PRL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sim and Zhang, 2015] Terence Sim and Li Zhang. Control- lable face privacy. In IEEE AFGR, volume 4, pages 1-8, 2015.","title":"Controllable face privacy","authors":"Zhang Sim, Terence Sim, Li Zhang","year":"2015","venue":"IEEE AFGR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Suo et al., 2011] Jinli Suo, Liang Lin, Shiguang Shan, Xilin Chen, and Wen Gao. High-resolution face fusion for gen- der conversion. IEEE TSMC, 41(2):226-237, 2011.","title":"High-resolution face fusion for gender conversion","authors":"Jinli Suo, Liang Lin, Shiguang Shan, Xilin Chen, Wen Gao","year":"2011","venue":"IEEE TSMC","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sweeney, 2002] Latanya Sweeney. k-anonymity: A model for protecting privacy. IJUFKS, 10(05):557-570, 2002.","title":"k-anonymity: A model for protecting privacy","authors":"Latanya Sweeney","year":"2002","venue":"IJUFKS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Viola et al., 2005] Paul Viola, Michael J Jones, and Daniel Snow. Detecting pedestrians using patterns of motion and appearance. IJCV, 63(2):153-161, 2005.","title":"Detecting pedestrians using patterns of motion and appearance","authors":"Paul Viola, Michael J Jones, Daniel Snow","year":"2005","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang and Kosinski, 2017] Yilun Wang and Michal Kosin- ski. Deep neural networks are more accurate than hu- mans at detecting sexual orientation from facial images. PsyArXiv preprint arXiv: 10.17605/OSF.IO/HV28A, 2017.","title":"Deep neural networks are more accurate than humans at detecting sexual orientation from facial images","authors":"Wang, Kosinski ;, Yilun Wang, Michal Kosinski","year":"2017","venue":null,"doi":"arxiv:10.17605/osf.io/hv28a","url":null,"internal_url":null},{"position":25,"raw":"[Wolf et al., 2011] Lior Wolf, Tal Hassner, and Itay Maoz. Face recognition in unconstrained videos with matched background similarity. In IEEE CVPR, pages 529-534, 2011.","title":"Face recognition in unconstrained videos with matched background similarity","authors":"Lior Wolf, Tal Hassner, Itay Maoz","year":"2011","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhou et al., 2018] Xiuzhuang Zhou, Kai Jin, Qian Chen, Min Xu, and Yuanyuan Shang. Multiple face tracking and recognition with identity-specific localized metric learn- ing. PR, 75:41-50, 2018.","title":"Multiple face tracking and recognition with identity-specific localized metric learning","authors":"Xiuzhuang Zhou, Kai Jin, Qian Chen, Min Xu, Yuanyuan Shang","year":"2018","venue":"PR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}