{"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/learning-to-detect-fake-face-images-in-the","title":"Learning to Detect Fake Face Images in the Wild","arxiv_id":"1809.08754","date":"2018-09-24","proceeding":null,"authors":["Chih-Chung Hsu","Chia-Yen Lee","Yi-Xiu Zhuang"],"abstract":"Although Generative Adversarial Network (GAN) can be used to generate the\nrealistic image, improper use of these technologies brings hidden concerns. For\nexample, GAN can be used to generate a tampered video for specific people and\ninappropriate events, creating images that are detrimental to a particular\nperson, and may even affect that personal safety. In this paper, we will\ndevelop a deep forgery discriminator (DeepFD) to efficiently and effectively\ndetect the computer-generated images. Directly learning a binary classifier is\nrelatively tricky since it is hard to find the common discriminative features\nfor judging the fake images generated from different GANs. To address this\nshortcoming, we adopt contrastive loss in seeking the typical features of the\nsynthesized images generated by different GANs and follow by concatenating a\nclassifier to detect such computer-generated images. Experimental results\ndemonstrate that the proposed DeepFD successfully detected 94.7% fake images\ngenerated by several state-of-the-art GANs.","url_abs":"http://arxiv.org/abs/1809.08754v3","url_pdf":"http://arxiv.org/pdf/1809.08754v3.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":"learning-to-detect-fake-face-images-in-the","repo_url":"https://github.com/jesse1029/Fake-Face-Images-Detection-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"fake-image-detection","task_name":"Fake Image Detection"},{"task_slug":"gan-image-forensics","task_name":"GAN image forensics"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.08754","atlas_url":"https://app.syntology.ai/?focus=1809.08754","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}