{"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/xai-based-detection-of-adversarial-attacks-on","title":"XAI-Based Detection of Adversarial Attacks on Deepfake Detectors","arxiv_id":"2403.02955","date":"2024-03-05","proceeding":null,"authors":["Ben Pinhasov","Raz Lapid","Rony Ohayon","Moshe Sipper","Yehudit Aperstein"],"abstract":"We introduce a novel methodology for identifying adversarial attacks on deepfake detectors using eXplainable Artificial Intelligence (XAI). In an era characterized by digital advancement, deepfakes have emerged as a potent tool, creating a demand for efficient detection systems. However, these systems are frequently targeted by adversarial attacks that inhibit their performance. We address this gap, developing a defensible deepfake detector by leveraging the power of XAI. The proposed methodology uses XAI to generate interpretability maps for a given method, providing explicit visualizations of decision-making factors within the AI models. We subsequently employ a pretrained feature extractor that processes both the input image and its corresponding XAI image. The feature embeddings extracted from this process are then used for training a simple yet effective classifier. Our approach contributes not only to the detection of deepfakes but also enhances the understanding of possible adversarial attacks, pinpointing potential vulnerabilities. Furthermore, this approach does not change the performance of the deepfake detector. The paper demonstrates promising results suggesting a potential pathway for future deepfake detection mechanisms. We believe this study will serve as a valuable contribution to the community, sparking much-needed discourse on safeguarding deepfake detectors.","url_abs":"https://arxiv.org/abs/2403.02955v2","url_pdf":"https://arxiv.org/pdf/2403.02955v2.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":"xai-based-detection-of-adversarial-attacks-on","repo_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"xai","task_name":"Explainable Artificial Intelligence (XAI)"},{"task_slug":"explainable-artificial-intelligence","task_name":"Explainable artificial intelligence"},{"task_slug":"face-swapping","task_name":"Face Swapping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.02955","atlas_url":"https://app.syntology.ai/?focus=2403.02955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02955"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","reach":{"status":"ok"}}],"summary":{"ran":10,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":13,"ran":11,"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":13,"samples":[{"code_sha256_prefix":"a47ffbdfd29954cc","entry":"add_gaussian_noise","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"robust_transforms.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/robust_transforms.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":"a47ffbdfd29954cc"}},{"code_sha256_prefix":"f5d10217406c3577","entry":"calc_videos_stats","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"summarize_stats.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/summarize_stats.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":"f5d10217406c3577"}},{"code_sha256_prefix":"4e33405073bc3c03","entry":"compress_decompress","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"robust_transforms.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/robust_transforms.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":"4e33405073bc3c03"}},{"code_sha256_prefix":"cdd770694303a504","entry":"get_boundingbox","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"detect_from_video.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/detect_from_video.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cdd770694303a504"}},{"code_sha256_prefix":"fe5c08e917b213f1","entry":"image_to_display","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"create_xai.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/create_xai.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":"fe5c08e917b213f1"}},{"code_sha256_prefix":"314c04b50c705d34","entry":"preprocess_image","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"auto_attack.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/auto_attack.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":"314c04b50c705d34"}},{"code_sha256_prefix":"8772d08802182519","entry":"summarize_frames","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"summarize_stats.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/summarize_stats.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":"8772d08802182519"}},{"code_sha256_prefix":"ce931adab65cc09f","entry":"summarize_videos","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"summarize_stats.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/summarize_stats.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":"ce931adab65cc09f"}},{"code_sha256_prefix":"b3853a178ee4150b","entry":"un_preprocess_image","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"create_xai.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/create_xai.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":"b3853a178ee4150b"}},{"code_sha256_prefix":"fc17be820e7e013a","entry":"un_preprocess_image","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"auto_attack.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/auto_attack.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":"fc17be820e7e013a"}},{"code_sha256_prefix":"31914a9457df6d95","entry":"xception","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"network/xception.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/network/xception.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":"31914a9457df6d95"}},{"code_sha256_prefix":"c29c17e60acd459b","entry":"display_images","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"create_xai.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/create_xai.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":"c29c17e60acd459b"}},{"code_sha256_prefix":"8452452bd0f5aa55","entry":"iterative_fgsm","repo":"razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors","repo_kind":"official","path":"attack_algos.py","file_url":"https://github.com/razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors/blob/HEAD/attack_algos.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":"8452452bd0f5aa55"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}