{"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/satellite-image-forgery-detection-and","title":"Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier","arxiv_id":"1802.04881","date":"2018-02-13","proceeding":null,"authors":["Sri Kalyan Yarlagadda","David Güera","Paolo Bestagini","Fengqing Maggie Zhu","Stefano Tubaro","Edward J. Delp"],"abstract":"Current satellite imaging technology enables shooting high-resolution\npictures of the ground. As any other kind of digital images, overhead pictures\ncan also be easily forged. However, common image forensic techniques are often\ndeveloped for consumer camera images, which strongly differ in their nature\nfrom satellite ones (e.g., compression schemes, post-processing, sensors,\netc.). Therefore, many accurate state-of-the-art forensic algorithms are bound\nto fail if blindly applied to overhead image analysis. Development of novel\nforensic tools for satellite images is paramount to assess their authenticity\nand integrity. In this paper, we propose an algorithm for satellite image\nforgery detection and localization. Specifically, we consider the scenario in\nwhich pixels within a region of a satellite image are replaced to add or remove\nan object from the scene. Our algorithm works under the assumption that no\nforged images are available for training. Using a generative adversarial\nnetwork (GAN), we learn a feature representation of pristine satellite images.\nA one-class support vector machine (SVM) is trained on these features to\ndetermine their distribution. Finally, image forgeries are detected as\nanomalies. The proposed algorithm is validated against different kinds of\nsatellite images containing forgeries of different size and shape.","url_abs":"http://arxiv.org/abs/1802.04881v1","url_pdf":"http://arxiv.org/pdf/1802.04881v1.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":"satellite-image-forgery-detection-and","repo_url":"https://github.com/Divyanshu-Singh-Chauhan/Digital-Image-Forgery-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-forgery-detection","task_name":"Image Forgery Detection"},{"task_slug":"one-class-classifier","task_name":"One-class classifier"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}