{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/semi-adversarial-networks-convolutional","title":"Semi-Adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images","arxiv_id":"1712.00321","date":"2017-12-01","proceeding":null,"authors":["Vahid Mirjalili","Sebastian Raschka","Anoop Namboodiri","Arun Ross"],"abstract":"In this paper, we design and evaluate a convolutional autoencoder that\nperturbs an input face image to impart privacy to a subject. Specifically, the\nproposed autoencoder transforms an input face image such that the transformed\nimage can be successfully used for face recognition but not for gender\nclassification. In order to train this autoencoder, we propose a novel training\nscheme, referred to as semi-adversarial training in this work. The training is\nfacilitated by attaching a semi-adversarial module consisting of a pseudo\ngender classifier and a pseudo face matcher to the autoencoder. The objective\nfunction utilized for training this network has three terms: one to ensure that\nthe perturbed image is a realistic face image; another to ensure that the\ngender attributes of the face are confounded; and a third to ensure that\nbiometric recognition performance due to the perturbed image is not impacted.\nExtensive experiments confirm the efficacy of the proposed architecture in\nextending gender privacy to face images.","url_abs":"http://arxiv.org/abs/1712.00321v3","url_pdf":"http://arxiv.org/pdf/1712.00321v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"semi-adversarial-networks-convolutional","repo_url":"https://github.com/iPRoBe-lab/semi-adversarial-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"gender-classification","task_name":"Gender Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}