{"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/trufor-leveraging-all-round-clues-for","title":"TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization","arxiv_id":"2212.10957","date":"2022-12-21","proceeding":"CVPR 2023 1","authors":["Fabrizio Guillaro","Davide Cozzolino","Avneesh Sud","Nicholas Dufour","Luisa Verdoliva"],"abstract":"In this paper we present TruFor, a forensic framework that can be applied to a large variety of image manipulation methods, from classic cheapfakes to more recent manipulations based on deep learning. We rely on the extraction of both high-level and low-level traces through a transformer-based fusion architecture that combines the RGB image and a learned noise-sensitive fingerprint. The latter learns to embed the artifacts related to the camera internal and external processing by training only on real data in a self-supervised manner. Forgeries are detected as deviations from the expected regular pattern that characterizes each pristine image. Looking for anomalies makes the approach able to robustly detect a variety of local manipulations, ensuring generalization. In addition to a pixel-level localization map and a whole-image integrity score, our approach outputs a reliability map that highlights areas where localization predictions may be error-prone. This is particularly important in forensic applications in order to reduce false alarms and allow for a large scale analysis. Extensive experiments on several datasets show that our method is able to reliably detect and localize both cheapfakes and deepfakes manipulations outperforming state-of-the-art works. Code is publicly available at https://grip-unina.github.io/TruFor/","url_abs":"https://arxiv.org/abs/2212.10957v3","url_pdf":"https://arxiv.org/pdf/2212.10957v3.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":[],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"image-forgery-detection","task_name":"Image Forgery Detection"},{"task_slug":"image-manipulation","task_name":"Image Manipulation"},{"task_slug":"image-manipulation-detection","task_name":"Image Manipulation Detection"},{"task_slug":"image-manipulation-localization","task_name":"Image Manipulation Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-manipulation-detection-on-coverage","task":"Image Manipulation Detection","dataset":"COVERAGE","model":"TruFor","rank_in_archive_order":3,"of":8,"metrics":{"AUC":".770","Balanced Accuracy":".680"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-casia-v1","task":"Image Manipulation Detection","dataset":"Casia V1+","model":"TruFor","rank_in_archive_order":4,"of":9,"metrics":{"AUC":".916","Balanced Accuracy":".813"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-cocoglide","task":"Image Manipulation Detection","dataset":"CocoGlide","model":"TruFor","rank_in_archive_order":3,"of":8,"metrics":{"AUC":".752","Balanced Accuracy":".639"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-columbia","task":"Image Manipulation Detection","dataset":"Columbia","model":"TruFor","rank_in_archive_order":1,"of":8,"metrics":{"AUC":".996","Balanced Accuracy":".984"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-dso-1","task":"Image Manipulation Detection","dataset":"DSO-1","model":"TruFor","rank_in_archive_order":2,"of":9,"metrics":{"AUC":".984","Balanced Accuracy":".930"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-casiav1","task":"Image Manipulation Localization","dataset":"CASIAv1(Protoclo-CAT)","model":"Trufor","rank_in_archive_order":2,"of":8,"metrics":{"Pixel Binary F1":"0.818"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-coverage","task":"Image Manipulation Localization","dataset":"COVERAGE","model":"TruFor","rank_in_archive_order":4,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".600"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-coverage-1","task":"Image Manipulation Localization","dataset":"COVERAGE(Protocol-CAT)","model":"Trufor","rank_in_archive_order":4,"of":8,"metrics":{"Pixel Binary F1":"0.457"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-casia-v1","task":"Image Manipulation Localization","dataset":"Casia V1+","model":"TruFor","rank_in_archive_order":7,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".737"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-cocoglide","task":"Image Manipulation Localization","dataset":"CocoGlide","model":"TruFor","rank_in_archive_order":5,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".523"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-columbia","task":"Image Manipulation Localization","dataset":"Columbia","model":"TruFor","rank_in_archive_order":5,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".859"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-columbia-1","task":"Image Manipulation Localization","dataset":"Columbia(Protocol-CAT)","model":"Trufor","rank_in_archive_order":4,"of":8,"metrics":{"Pixel Binary F1":"0.885"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-dso-1","task":"Image Manipulation Localization","dataset":"DSO-1","model":"TruFor","rank_in_archive_order":1,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".930"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-nist16","task":"Image Manipulation Localization","dataset":"NIST16(Protocol-CAT)","model":"Trufor","rank_in_archive_order":5,"of":8,"metrics":{"Pixel Binary F1":"0.348"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.10957","atlas_url":"https://app.syntology.ai/?focus=2212.10957","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}