{"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/adversarial-perturbations-fool-deepfake","title":"Adversarial Perturbations Fool Deepfake Detectors","arxiv_id":"2003.10596","date":"2020-03-24","proceeding":null,"authors":["Apurva Gandhi","Shomik Jain"],"abstract":"This work uses adversarial perturbations to enhance deepfake images and fool common deepfake detectors. We created adversarial perturbations using the Fast Gradient Sign Method and the Carlini and Wagner L2 norm attack in both blackbox and whitebox settings. Detectors achieved over 95% accuracy on unperturbed deepfakes, but less than 27% accuracy on perturbed deepfakes. We also explore two improvements to deepfake detectors: (i) Lipschitz regularization, and (ii) Deep Image Prior (DIP). Lipschitz regularization constrains the gradient of the detector with respect to the input in order to increase robustness to input perturbations. The DIP defense removes perturbations using generative convolutional neural networks in an unsupervised manner. Regularization improved the detection of perturbed deepfakes on average, including a 10% accuracy boost in the blackbox case. The DIP defense achieved 95% accuracy on perturbed deepfakes that fooled the original detector, while retaining 98% accuracy in other cases on a 100 image subsample.","url_abs":"https://arxiv.org/abs/2003.10596v2","url_pdf":"https://arxiv.org/pdf/2003.10596v2.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":"adversarial-perturbations-fool-deepfake","repo_url":"https://github.com/ApGa/adversarial_deepfakes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-swapping","task_name":"Face Swapping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.10596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10596"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ApGa/adversarial_deepfakes","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"24610ea98446fa84","entry":"add_noise","repo":"ApGa/adversarial_deepfakes","repo_kind":"official","path":"classifier.py","file_url":"https://github.com/ApGa/adversarial_deepfakes/blob/HEAD/classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24610ea98446fa84"}},{"code_sha256_prefix":"c54694cd7ab40f55","entry":"bim","repo":"ApGa/adversarial_deepfakes","repo_kind":"official","path":"adv_examples.py","file_url":"https://github.com/ApGa/adversarial_deepfakes/blob/HEAD/adv_examples.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c54694cd7ab40f55"}},{"code_sha256_prefix":"969781f75548142e","entry":"fgsm","repo":"ApGa/adversarial_deepfakes","repo_kind":"official","path":"adv_examples.py","file_url":"https://github.com/ApGa/adversarial_deepfakes/blob/HEAD/adv_examples.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"969781f75548142e"}},{"code_sha256_prefix":"c1a53b05fe8519cd","entry":"ifgsm","repo":"ApGa/adversarial_deepfakes","repo_kind":"official","path":"adv_examples.py","file_url":"https://github.com/ApGa/adversarial_deepfakes/blob/HEAD/adv_examples.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1a53b05fe8519cd"}},{"code_sha256_prefix":"24f2b9a08b2cebda","entry":"lipshitz_regularization","repo":"ApGa/adversarial_deepfakes","repo_kind":"official","path":"classifier.py","file_url":"https://github.com/ApGa/adversarial_deepfakes/blob/HEAD/classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24f2b9a08b2cebda"}},{"code_sha256_prefix":"0e2498182c6b0d20","entry":"train_model","repo":"ApGa/adversarial_deepfakes","repo_kind":"official","path":"classifier.py","file_url":"https://github.com/ApGa/adversarial_deepfakes/blob/HEAD/classifier.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e2498182c6b0d20"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}