{"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/aird-adversarial-learning-framework-for-image","title":"AIRD: Adversarial Learning Framework for Image Repurposing Detection","arxiv_id":"1903.00788","date":"2019-03-02","proceeding":"CVPR 2019 6","authors":["Ayush Jaiswal","Yue Wu","Wael Abd-Almageed","Iacopo Masi","Premkumar Natarajan"],"abstract":"Image repurposing is a commonly used method for spreading misinformation on\nsocial media and online forums, which involves publishing untampered images\nwith modified metadata to create rumors and further propaganda. While manual\nverification is possible, given vast amounts of verified knowledge available on\nthe internet, the increasing prevalence and ease of this form of semantic\nmanipulation call for the development of robust automatic ways of assessing the\nsemantic integrity of multimedia data. In this paper, we present a novel method\nfor image repurposing detection that is based on the real-world adversarial\ninterplay between a bad actor who repurposes images with counterfeit metadata\nand a watchdog who verifies the semantic consistency between images and their\naccompanying metadata, where both players have access to a reference dataset of\nverified content, which they can use to achieve their goals. The proposed\nmethod exhibits state-of-the-art performance on location-identity,\nsubject-identity and painting-artist verification, showing its efficacy across\na diverse set of scenarios.","url_abs":"http://arxiv.org/abs/1903.00788v3","url_pdf":"http://arxiv.org/pdf/1903.00788v3.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":"aird-adversarial-learning-framework-for-image","repo_url":"https://github.com/isi-vista/AIRD-Datasets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"misinformation","task_name":"Misinformation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.00788","atlas_url":"https://app.syntology.ai/?focus=1903.00788","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}