{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/forensic-similarity-for-digital-images","title":"Forensic Similarity for Digital Images","arxiv_id":"1902.04684","date":"2019-02-13","proceeding":null,"authors":["Owen Mayer","Matthew C. Stamm"],"abstract":"In this paper we introduce a new digital image forensics approach called forensic similarity, which determines whether two image patches contain the same forensic trace or different forensic traces. One benefit of this approach is that prior knowledge, e.g. training samples, of a forensic trace are not required to make a forensic similarity decision on it in the future. To do this, we propose a two part deep-learning system composed of a CNN-based feature extractor and a three-layer neural network, called the similarity network. This system maps pairs of image patches to a score indicating whether they contain the same or different forensic traces. We evaluated system accuracy of determining whether two image patches were 1) captured by the same or different camera model, 2) manipulated by the same or different editing operation, and 3) manipulated by the same or different manipulation parameter, given a particular editing operation. Experiments demonstrate applicability to a variety of forensic traces, and importantly show efficacy on \"unknown\" forensic traces that were not used to train the system. Experiments also show that the proposed system significantly improves upon prior art, reducing error rates by more than half. Furthermore, we demonstrated the utility of the forensic similarity approach in two practical applications: forgery detection and localization, and database consistency verification.","url_abs":"https://arxiv.org/abs/1902.04684v2","url_pdf":"https://arxiv.org/pdf/1902.04684v2.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":"forensic-similarity-for-digital-images","repo_url":"https://gitlab.com/MISLgit/forensic-similarity-for-digital-images","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-forensics","task_name":"Image Forensics"},{"task_slug":"image-manipulation-detection","task_name":"Image Manipulation Detection"}],"methods":[{"method_slug":"accumulating-eligibility-trace","method_name":"Accumulating Eligibility Trace"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-manipulation-detection-on-casia-osn","task":"Image Manipulation Detection","dataset":"CASIA (OSN-transmitted - Facebook)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.537","F-score":"0.157","Intersection over Union":"0.094"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-casia-osn-1","task":"Image Manipulation Detection","dataset":"CASIA (OSN-transmitted - Wechat)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.532","Intersection over Union":"0.153","f-Score":"0.091"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-casia-osn-3","task":"Image Manipulation Detection","dataset":"CASIA (OSN-transmitted - Weibo)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.542","Intersection over Union":"0.100","f-Score":"0.165"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-casia-osn-2","task":"Image Manipulation Detection","dataset":"CASIA (OSN-transmitted - Whatsapp)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.525","Intersection over Union":"0.091","f-Score":"0.151"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-columbia-osn","task":"Image Manipulation Detection","dataset":"Columbia (OSN-transmitted - Facebook)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.607","Intersection over Union":"0.304","f-Score":"0.450"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-columbia-osn-1","task":"Image Manipulation Detection","dataset":"Columbia (OSN-transmitted - Wechat)","model":"ForSim","rank_in_archive_order":3,"of":4,"metrics":{"AUC":"0.650","Intersection over Union":"0.354","f-Score":"0.496"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-columbia-osn-3","task":"Image Manipulation Detection","dataset":"Columbia (OSN-transmitted - Weibo)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.610","Intersection over Union":"0.312","f-Score":"0.453"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-columbia-osn-2","task":"Image Manipulation Detection","dataset":"Columbia (OSN-transmitted - Whatsapp)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.595","Intersection over Union":"0.294","f-Score":"0.436"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-dso-osn","task":"Image Manipulation Detection","dataset":"DSO (OSN-transmitted - Facebook)","model":"ForSim","rank_in_archive_order":3,"of":4,"metrics":{"AUC":"0.689","Intersection over Union":"0.238","f-Score":"0.356"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-dso-osn-1","task":"Image Manipulation Detection","dataset":"DSO (OSN-transmitted - Wechat)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.564","Intersection over Union":"0.147","f-Score":"0.247"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-dso-osn-3","task":"Image Manipulation Detection","dataset":"DSO (OSN-transmitted - Weibo)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.568","Intersection over Union":"0.165","f-Score":"0.260"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-dso-osn-2","task":"Image Manipulation Detection","dataset":"DSO (OSN-transmitted - Whatsapp)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.542","Intersection over Union":"0.139","f-Score":"0.233"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-nist-osn","task":"Image Manipulation Detection","dataset":"NIST (OSN-transmitted - Facebook)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.580","Intersection over Union":"0.085","f-Score":"0.140"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-nist-osn-1","task":"Image Manipulation Detection","dataset":"NIST (OSN-transmitted - Wechat)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.581","Intersection over Union":"0.082","f-Score":"0.136"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-nist-osn-3","task":"Image Manipulation Detection","dataset":"NIST (OSN-transmitted - Weibo)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.581","Intersection over Union":"0.094","f-Score":"0.150"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-detection-on-nist-osn-2","task":"Image Manipulation Detection","dataset":"NIST (OSN-transmitted - Whatsapp)","model":"ForSim","rank_in_archive_order":4,"of":4,"metrics":{"AUC":"0.586","Intersection over Union":"0.082","f-Score":"0.137"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.04684","atlas_url":"https://app.syntology.ai/?focus=1902.04684","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1902.04684"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.04684\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.04684"},"call":"get_concepts_for_paper(arxiv_id=\"1902.04684\")"}],"by_repo":[{"repo":"gitlab.com/MISLgit/forensic-similarity-for-digital-images","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a1de2d9a4cec7295bcd83575aea338db581972a541a0cd1407e235e6f31094de","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}