{"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/a-comprehensive-analysis-of-ai-biases-in","title":"Analyzing Fairness in Deepfake Detection With Massively Annotated Databases","arxiv_id":"2208.05845","date":"2022-08-11","proceeding":null,"authors":["Ying Xu","Philipp Terhörst","Kiran Raja","Marius Pedersen"],"abstract":"In recent years, image and video manipulations with Deepfake have become a severe concern for security and society. Many detection models and datasets have been proposed to detect Deepfake data reliably. However, there is an increased concern that these models and training databases might be biased and, thus, cause Deepfake detectors to fail. In this work, we investigate factors causing biased detection in public Deepfake datasets by (a) creating large-scale demographic and non-demographic attribute annotations with 47 different attributes for five popular Deepfake datasets and (b) comprehensively analysing attributes resulting in AI-bias of three state-of-the-art Deepfake detection backbone models on these datasets. The analysis shows how various attributes influence a large variety of distinctive attributes (from over 65M labels) on the detection performance which includes demographic (age, gender, ethnicity) and non-demographic (hair, skin, accessories, etc.) attributes. The results examined datasets show limited diversity and, more importantly, show that the utilised Deepfake detection backbone models are strongly affected by investigated attributes making them not fair across attributes. The Deepfake detection backbone methods trained on such imbalanced/biased datasets result in incorrect detection results leading to generalisability, fairness, and security issues. Our findings and annotated datasets will guide future research to evaluate and mitigate bias in Deepfake detection techniques. The annotated datasets and the corresponding code are publicly available.","url_abs":"https://arxiv.org/abs/2208.05845v4","url_pdf":"https://arxiv.org/pdf/2208.05845v4.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":"a-comprehensive-analysis-of-ai-biases-in","repo_url":"https://github.com/pterhoer/DeepFakeAnnotations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-comprehensive-analysis-of-ai-biases-in","repo_url":"https://github.com/xuyingzhongguo/deepfakeannotations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-comprehensive-analysis-of-ai-biases-in","repo_url":"https://github.com/leaffeall/DFS-GDD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-comprehensive-analysis-of-ai-biases-in","repo_url":"https://github.com/purdue-m2/auc_fairness_with_noisy_groups","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-comprehensive-analysis-of-ai-biases-in","repo_url":"https://github.com/purdue-m2/fairness-generalization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-comprehensive-analysis-of-ai-biases-in","repo_url":"https://github.com/purdue-m2/robust_fairness_withNoisy_labels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[{"slug":"dmad","name":"DMAD","full_name":"Deepfake Massively Annotated Databases"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.05845","atlas_url":"https://app.syntology.ai/?focus=2208.05845","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":"2208.05845"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2208.05845\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2208.05845"},"call":"get_concepts_for_paper(arxiv_id=\"2208.05845\")"}],"by_repo":[{"repo":"pterhoer/DeepFakeAnnotations","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xuyingzhongguo/deepfakeannotations","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"leaffeall/DFS-GDD","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"purdue-m2/auc_fairness_with_noisy_groups","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.10451"],"harvested_for_calls":[{"arxiv_id":"2208.10451","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.10451"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.10451\")"}]},{"repo":"purdue-m2/fairness-generalization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.17229"],"harvested_for_calls":[{"arxiv_id":"2402.17229","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.17229"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.17229\")"}]},{"repo":"purdue-m2/robust_fairness_withNoisy_labels","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"41c3ab0560fa79bbab63204533f8390d9357cf02ec373a41adc1ed72442b7e29","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}