{"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/poisoned-forgery-face-towards-backdoor","title":"Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection","arxiv_id":"2402.11473","date":"2024-02-18","proceeding":null,"authors":["Jiawei Liang","Siyuan Liang","Aishan Liu","Xiaojun Jia","Junhao Kuang","Xiaochun Cao"],"abstract":"The proliferation of face forgery techniques has raised significant concerns within society, thereby motivating the development of face forgery detection methods. These methods aim to distinguish forged faces from genuine ones and have proven effective in practical applications. However, this paper introduces a novel and previously unrecognized threat in face forgery detection scenarios caused by backdoor attack. By embedding backdoors into models and incorporating specific trigger patterns into the input, attackers can deceive detectors into producing erroneous predictions for forged faces. To achieve this goal, this paper proposes \\emph{Poisoned Forgery Face} framework, which enables clean-label backdoor attacks on face forgery detectors. Our approach involves constructing a scalable trigger generator and utilizing a novel convolving process to generate translation-sensitive trigger patterns. Moreover, we employ a relative embedding method based on landmark-based regions to enhance the stealthiness of the poisoned samples. Consequently, detectors trained on our poisoned samples are embedded with backdoors. Notably, our approach surpasses SoTA backdoor baselines with a significant improvement in attack success rate (+16.39\\% BD-AUC) and reduction in visibility (-12.65\\% $L_\\infty$). Furthermore, our attack exhibits promising performance against backdoor defenses. We anticipate that this paper will draw greater attention to the potential threats posed by backdoor attacks in face forgery detection scenarios. Our codes will be made available at \\url{https://github.com/JWLiang007/PFF}","url_abs":"https://arxiv.org/abs/2402.11473v1","url_pdf":"https://arxiv.org/pdf/2402.11473v1.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":"poisoned-forgery-face-towards-backdoor","repo_url":"https://github.com/jwliang007/pff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11473"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/JWLiang007/PFF","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jwliang007/pff","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"571f70c187fecd59","entry":"compute_accuray","repo":"jwliang007/pff","repo_kind":"official","path":"src/train_sbi_bd.py","file_url":"https://github.com/jwliang007/pff/blob/HEAD/src/train_sbi_bd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"571f70c187fecd59"}},{"code_sha256_prefix":"04b8aaa5c752fcf5","entry":"extract_face","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/inference/preprocess.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04b8aaa5c752fcf5"}},{"code_sha256_prefix":"dbcad420678ad0a4","entry":"init_dfd","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/inference/datasets.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dbcad420678ad0a4"}},{"code_sha256_prefix":"e0db134a43076a0b","entry":"init_dfdcp","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/inference/datasets.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/datasets.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0db134a43076a0b"}},{"code_sha256_prefix":"e22aae0623cbac29","entry":"init_ff","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/inference/datasets.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e22aae0623cbac29"}},{"code_sha256_prefix":"4f116960047d860c","entry":"load_input","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/preprocess/add_bd_trigger.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/preprocess/add_bd_trigger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f116960047d860c"}},{"code_sha256_prefix":"a0a5efc8b51a1b93","entry":"match_file","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/inference/preprocess.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0a5efc8b51a1b93"}},{"code_sha256_prefix":"102d81df8cb3fed0","entry":"SBI_BD_Dataset","repo":"jwliang007/pff","repo_kind":"official","path":"src/utils/sbi_bd.py","file_url":"https://github.com/jwliang007/pff/blob/HEAD/src/utils/sbi_bd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"102d81df8cb3fed0"}},{"code_sha256_prefix":"73f6f4be641ec794","entry":"extract_frames","repo":"JWLiang007/PFF","repo_kind":"official","path":"src/inference/preprocess.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73f6f4be641ec794"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}