{"url":"/task/face-anti-spoofing","name":"Face Anti-Spoofing","slug":"face-anti-spoofing","description_markdown":"Facial anti-spoofing is the task of preventing false facial verification by using a photo, video, mask or a different substitute for an authorized person’s face. Some examples of attacks:\r\n\r\n- **Print attack**: The attacker uses someone’s photo. The image is printed or displayed on a digital device.\r\n\r\n- **Replay/video attack**: A more sophisticated way to trick the system, which usually requires a looped video of a victim’s face. This approach ensures behaviour and facial movements to look more ‘natural’ compared to holding someone’s photo.\r\n\r\n- **3D mask attack**: During this type of attack, a mask is used as the tool of choice for spoofing. It’s an even more sophisticated attack than playing a face video. In addition to natural facial movements, it enables ways to deceive some extra layers of protection such as depth sensors.\r\n\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing](https://github.com/XgTu/GFA-CNN) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":204,"papers_with_code":78,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":0,"parent_tasks":3},"benchmarks":[{"leaderboard":"/sota/face-anti-spoofing-on-siw-protocol-3","slug":"face-anti-spoofing-on-siw-protocol-3","dataset":"SiW (Protocol 3)","dataset_url":"/dataset/siw","rows_in_archive":7,"metrics":["ACER"],"first_row_in_archive_order":{"model":"FasTCo + OAP","paper_title":"Online Adaptive Personalization for Face Anti-spoofing","paper_url":"/paper/online-adaptive-personalization-for-face-anti","paper_date":"2022-07-04","arxiv_id":"2207.12272","code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-celeba-spoof-enroll5","slug":"face-anti-spoofing-on-celeba-spoof-enroll5","dataset":"CelebA-Spoof-Enroll5","dataset_url":"/dataset/celeba-spoof-enroll","rows_in_archive":5,"metrics":["AUC"],"first_row_in_archive_order":{"model":"ResNet 18 Personalized","paper_title":"A personalized benchmark for face anti-spoofing","paper_url":"/paper/a-personalized-benchmark-for-face-anti","paper_date":"2022-01-05","arxiv_id":null,"code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-siw-enroll5","slug":"face-anti-spoofing-on-siw-enroll5","dataset":"SiW-Enroll5","dataset_url":"/dataset/siw-enroll","rows_in_archive":5,"metrics":["AUC"],"first_row_in_archive_order":{"model":"ResNet18 Personalized","paper_title":"A personalized benchmark for face anti-spoofing","paper_url":"/paper/a-personalized-benchmark-for-face-anti","paper_date":"2022-01-05","arxiv_id":null,"code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-oulu-npu","slug":"face-anti-spoofing-on-oulu-npu","dataset":"OULU-NPU","dataset_url":"/dataset/oulu-npu","rows_in_archive":4,"metrics":["ACER","HTER"],"first_row_in_archive_order":{"model":"Bi-FPNFAS","paper_title":"Bi-FPNFAS: Bi-Directional Feature Pyramid Network for Pixel-Wise Face Anti-Spoofing by Leveraging Fourier Spectra","paper_url":"/paper/bi-fpnfas-bi-directional-feature-pyramid","paper_date":"2021-04-15","arxiv_id":null,"code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-replay-attack","slug":"face-anti-spoofing-on-replay-attack","dataset":"Replay-Attack","dataset_url":"/dataset/replay-attack","rows_in_archive":4,"metrics":["EER","HTER"],"first_row_in_archive_order":{"model":"Entry-V2","paper_title":"Generalizable Method for Face Anti-Spoofing with Semi-Supervised Learning","paper_url":"/paper/generalizable-method-for-face-anti-spoofing","paper_date":"2022-06-13","arxiv_id":"2206.06510","code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"},{"title":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection"},{"title":"xix-ai/antispoofing","url":"https://github.com/xix-ai/antispoofing"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-msu-mfsd","slug":"face-anti-spoofing-on-msu-mfsd","dataset":"MSU-MFSD","dataset_url":"/dataset/msu-mfsd","rows_in_archive":3,"metrics":["Equal Error Rate","HTER"],"first_row_in_archive_order":{"model":"Entry-V2","paper_title":"Generalizable Method for Face Anti-Spoofing with Semi-Supervised Learning","paper_url":"/paper/generalizable-method-for-face-anti-spoofing","paper_date":"2022-06-13","arxiv_id":"2206.06510","code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"},{"title":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection"},{"title":"xix-ai/antispoofing","url":"https://github.com/xix-ai/antispoofing"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-casia-mfsd","slug":"face-anti-spoofing-on-casia-mfsd","dataset":"CASIA-MFSD","dataset_url":"/dataset/casia-mfsd","rows_in_archive":2,"metrics":["EER","HTER"],"first_row_in_archive_order":{"model":"3D Synthesis (balancing sampling)","paper_title":"Improving Face Anti-Spoofing by 3D Virtual Synthesis","paper_url":"/paper/improving-face-anti-spoofing-by-3d-virtual","paper_date":"2019-01-02","arxiv_id":"1901.00488","code_links":[{"title":"sicxu/Deep3DFaceRecon_pytorch","url":"https://github.com/sicxu/Deep3DFaceRecon_pytorch"},{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"},{"title":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection"}],"syntology":null}},{"leaderboard":"/sota/face-anti-spoofing-on-mlfp","slug":"face-anti-spoofing-on-mlfp","dataset":"MLFP","dataset_url":"/dataset/mlfp","rows_in_archive":1,"metrics":["HTER"],"first_row_in_archive_order":{"model":"MCCNN (BCE+OCCL)-GMM","paper_title":"Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networks","paper_url":"/paper/learning-one-class-representations-for-face","paper_date":"2020-07-22","arxiv_id":"2007.11457","code_links":[{"title":"FaceOnLive/Face-Liveness-Detection-SDK-Linux","url":"https://github.com/FaceOnLive/Face-Liveness-Detection-SDK-Linux"},{"title":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection"},{"title":"anjith2006/bob.paper.oneclass_mccnn_2019","url":"https://github.com/anjith2006/bob.paper.oneclass_mccnn_2019"}],"syntology":null}}],"datasets":[{"url":"/dataset/replay-attack","name":"Replay-Attack","full_name":"","num_papers_in_archive":133},{"url":"/dataset/msu-mfsd","name":"MSU-MFSD","full_name":"","num_papers_in_archive":89},{"url":"/dataset/casia-mfsd","name":"CASIA-MFSD","full_name":"CASIA-MFSD","num_papers_in_archive":58},{"url":"/dataset/siw","name":"SiW","full_name":"Spoofing in the Wild","num_papers_in_archive":51},{"url":"/dataset/casia-fasd","name":"CASIA-FASD","full_name":"CASIA-FASD","num_papers_in_archive":42},{"url":"/dataset/celeba-spoof","name":"CelebA-Spoof","full_name":"","num_papers_in_archive":28},{"url":"/dataset/casia-surf","name":"CASIA-SURF","full_name":"","num_papers_in_archive":24},{"url":"/dataset/replay-mobile-1","name":"Replay-Mobile","full_name":"Replay-Mobile","num_papers_in_archive":18},{"url":"/dataset/hifimask","name":"HiFiMask","full_name":"CASIA-SURF HiFiMask","num_papers_in_archive":14},{"url":"/dataset/hq-wmca","name":"HQ-WMCA","full_name":"High-Quality Wide Multi-Channel Attack database","num_papers_in_archive":9},{"url":"/dataset/oulu-npu","name":"OULU-NPU","full_name":"","num_papers_in_archive":8},{"url":"/dataset/mebal","name":"mEBAL","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mlfp","name":"MLFP","full_name":"Multispectral Latex Mask based Video Face Presentation Attack","num_papers_in_archive":4},{"url":"/dataset/celeba-spoof-enroll","name":"CelebA-Spoof-Enroll","full_name":"","num_papers_in_archive":3},{"url":"/dataset/siw-enroll","name":"SiW-Enroll","full_name":"","num_papers_in_archive":3},{"url":"/dataset/suhifimask","name":"SuHiFiMask","full_name":"Surveillance High-Fidelity Mask","num_papers_in_archive":2},{"url":"/dataset/swax","name":"SWAX","full_name":"Sense Wax Attack dataset","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/depth-and-camera-motion","name":"Depth And Camera Motion"},{"url":"/task/facial-recognition-and-modelling","name":"Facial Recognition and Modelling"},{"url":"/task/visual-odometry","name":"Visual Odometry"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":78,"tagged_in_all":204,"items":[{"url":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","arxiv_id":"1512.03385","repositories_listed":484,"syntology":{"n":377,"n_ran":230,"n_unverified":147,"n_pointer_only":187}},{"url":"/paper/very-deep-convolutional-networks-for-large","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","date":"2014-09-04","arxiv_id":"1409.1556","repositories_listed":305,"syntology":{"n":122,"n_ran":12,"n_unverified":110,"n_pointer_only":4}},{"url":"/paper/deep-pixel-wise-binary-supervision-for-face","title":"Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection","date":"2019-07-09","arxiv_id":"1907.04047","repositories_listed":7,"syntology":null},{"url":"/paper/learning-generalized-spoof-cues-for-face-anti","title":"Learning Generalized Spoof Cues for Face Anti-spoofing","date":"2020-05-08","arxiv_id":"2005.03922","repositories_listed":6,"syntology":null},{"url":"/paper/deep-spatial-gradient-and-temporal-depth","title":"Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing","date":"2020-03-18","arxiv_id":"2003.08061","repositories_listed":5,"syntology":null},{"url":"/paper/searching-central-difference-convolutional","title":"Searching Central Difference Convolutional Networks for Face Anti-Spoofing","date":"2020-03-09","arxiv_id":"2003.04092","repositories_listed":5,"syntology":null},{"url":"/paper/cross-database-liveness-detection-insights","title":"Cross-Database Liveness Detection: Insights from Comparative Biometric Analysis","date":"2024-01-29","arxiv_id":"2401.16232","repositories_listed":4,"syntology":null},{"url":"/paper/learn-convolutional-neural-network-for-face","title":"Learn Convolutional Neural Network for Face Anti-Spoofing","date":"2014-08-24","arxiv_id":"1408.5601","repositories_listed":4,"syntology":null},{"url":"/paper/a-visualization-method-for-data-domain","title":"A visualization method for data domain changes in CNN networks and the optimization method for selecting thresholds in classification tasks","date":"2024-04-19","arxiv_id":"2404.12602","repositories_listed":3,"syntology":null},{"url":"/paper/joint-physical-digital-facial-attack","title":"Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues","date":"2024-04-12","arxiv_id":"2404.08450","repositories_listed":3,"syntology":null},{"url":"/paper/domain-generalized-face-anti-spoofing-with","title":"Domain-Generalized Face Anti-Spoofing with Unknown Attacks","date":"2023-10-18","arxiv_id":"2310.11758","repositories_listed":3,"syntology":null},{"url":"/paper/flip-cross-domain-face-anti-spoofing-with-1","title":"FLIP: Cross-domain Face Anti-spoofing with Language Guidance","date":"2023-09-28","arxiv_id":"2309.16649","repositories_listed":3,"syntology":null},{"url":"/paper/s-adapter-generalizing-vision-transformer-for","title":"S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens","date":"2023-09-07","arxiv_id":"2309.04038","repositories_listed":3,"syntology":null},{"url":"/paper/enhancing-mobile-face-anti-spoofing-a-robust","title":"Enhancing Mobile Face Anti-Spoofing: A Robust Framework for Diverse Attack Types under Screen Flash","date":"2023-08-29","arxiv_id":"2308.15346","repositories_listed":3,"syntology":null},{"url":"/paper/advfas-a-robust-face-anti-spoofing-framework","title":"AdvFAS: A robust face anti-spoofing framework against adversarial examples","date":"2023-08-04","arxiv_id":"2308.02116","repositories_listed":3,"syntology":null},{"url":"/paper/deep-ensemble-learning-with-frame-skipping","title":"Deep Ensemble Learning with Frame Skipping for Face Anti-Spoofing","date":"2023-07-06","arxiv_id":"2307.02858","repositories_listed":3,"syntology":null},{"url":"/paper/joint-statistical-and-causal-feature","title":"Joint Statistical and Causal Feature Modulated Face Anti-Spoofing","date":"2023-07-04","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/latent-distribution-adjusting-for-face-anti","title":"Latent Distribution Adjusting for Face Anti-Spoofing","date":"2023-05-16","arxiv_id":"2305.09285","repositories_listed":3,"syntology":null},{"url":"/paper/wild-face-anti-spoofing-challenge-2023","title":"Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results","date":"2023-04-12","arxiv_id":"2304.05753","repositories_listed":3,"syntology":null},{"url":"/paper/multi-domain-learning-for-updating-face-anti","title":"Multi-domain Learning for Updating Face Anti-spoofing Models","date":"2022-08-23","arxiv_id":"2208.11148","repositories_listed":3,"syntology":null},{"url":"/paper/generalizable-method-for-face-anti-spoofing","title":"Generalizable Method for Face Anti-Spoofing with Semi-Supervised Learning","date":"2022-06-13","arxiv_id":"2206.06510","repositories_listed":3,"syntology":null},{"url":"/paper/learning-one-class-representations-for-face","title":"Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networks","date":"2020-07-22","arxiv_id":"2007.11457","repositories_listed":3,"syntology":null},{"url":"/paper/190409290","title":"FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing","date":"2019-04-22","arxiv_id":"1904.09290","repositories_listed":3,"syntology":null},{"url":"/paper/improving-face-anti-spoofing-by-3d-virtual","title":"Improving Face Anti-Spoofing by 3D Virtual Synthesis","date":"2019-01-02","arxiv_id":"1901.00488","repositories_listed":3,"syntology":null},{"url":"/paper/foundpad-foundation-models-reloaded-for-face","title":"FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection","date":"2025-01-06","arxiv_id":"2501.02892","repositories_listed":2,"syntology":null},{"url":"/paper/suppress-and-rebalance-towards-generalized","title":"Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing","date":"2024-02-29","arxiv_id":"2402.19298","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/shield-an-evaluation-benchmark-for-face","title":"SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models","date":"2024-02-06","arxiv_id":"2402.04178","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/one-class-face-anti-spoofing-via-spoof-cue","title":"One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/patchnet-a-simple-face-anti-spoofing","title":"PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition","date":"2022-03-27","arxiv_id":"2203.14325","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-meets-liveness-detection-recent","title":"Deep Learning meets Liveness Detection: Recent Advancements and Challenges","date":"2021-12-29","arxiv_id":"2112.14796","repositories_listed":2,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}