{"url":"/task/audio-deepfake-detection","name":"Audio Deepfake Detection","slug":"audio-deepfake-detection","description_markdown":"Nowadays, deepfake is now generically used by the media\r\nor people to refer to any audio or video in which important\r\nattributes have been either digitally altered or swapped,\r\nwith the help of artificial intelligence (AI). Audio deepfake detection is a task that aims to distinguish genuine utterances from fake ones via machine\r\nlearning techniques.","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":74,"papers_with_code":35,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":3,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/audio-deepfake-detection-on-asvspoof-2021","slug":"audio-deepfake-detection-on-asvspoof-2021","dataset":"ASVspoof 2021","dataset_url":"/dataset/asvspoof-2021","rows_in_archive":8,"metrics":["21LA EER","21DF EER"],"first_row_in_archive_order":{"model":"XLSR-Mamba","paper_title":"XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection","paper_url":"/paper/xlsr-mamba-a-dual-column-bidirectional-state","paper_date":"2024-11-15","arxiv_id":"2411.10027","code_links":[{"title":"swagshaw/xlsr-mamba","url":"https://github.com/swagshaw/xlsr-mamba"}],"syntology":null}},{"leaderboard":"/sota/audio-deepfake-detection-on-fakeorreal","slug":"audio-deepfake-detection-on-fakeorreal","dataset":"FakeOrReal","dataset_url":null,"rows_in_archive":1,"metrics":["EER"],"first_row_in_archive_order":{"model":"rawnet_lite.pt","paper_title":"End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation","paper_url":"/paper/end-to-end-audio-deepfake-detection-from-raw","paper_date":"2025-04-29","arxiv_id":"2504.20923","code_links":[{"title":"adipiz99/RawNetLite","url":"https://github.com/adipiz99/RawNetLite"}],"syntology":null}}],"datasets":[{"url":"/dataset/asvspoof-2021","name":"ASVspoof 2021","full_name":"ASVspoof 2021 Dataset","num_papers_in_archive":8},{"url":"/dataset/fakemusiccaps","name":"FakeMusicCaps","full_name":"","num_papers_in_archive":4},{"url":"/dataset/sonics","name":"SONICS","full_name":"Synthetic Or Not - Identifying Counterfeit Songs","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/deepfake-detection","name":"DeepFake Detection"},{"url":"/task/speaker-verification","name":"Speaker Verification"}],"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":35,"tagged_in_all":74,"items":[{"url":"/paper/automatic-speaker-verification-spoofing-and","title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","date":"2022-02-24","arxiv_id":"2202.12233","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/audio-deepfake-detection-with-self-supervised-1","title":"Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier","date":"2024-10-28","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/sonics-synthetic-or-not-identifying","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","date":"2024-08-26","arxiv_id":"2408.14080","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/wavlm-model-ensemble-for-audio-deepfake","title":"WavLM model ensemble for audio deepfake detection","date":"2024-08-14","arxiv_id":"2408.07414","repositories_listed":2,"syntology":null},{"url":"/paper/wavefake-a-data-set-to-facilitate-audio","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","date":"2021-11-04","arxiv_id":"2111.02813","repositories_listed":2,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/aasist-audio-anti-spoofing-using-integrated","title":"AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks","date":"2021-10-04","arxiv_id":"2110.01200","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/few-shot-speech-deepfake-detection-adaptation","title":"Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes","date":"2025-05-29","arxiv_id":"2505.23619","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-audio-deepfake-detection-from-raw","title":"End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation","date":"2025-04-29","arxiv_id":"2504.20923","repositories_listed":1,"syntology":null},{"url":"/paper/detect-all-type-deepfake-audio-wavelet-prompt","title":"Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception","date":"2025-04-09","arxiv_id":"2504.06753","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-the-robustness-of-audio-deepfake","title":"Measuring the Robustness of Audio Deepfake Detectors","date":"2025-03-21","arxiv_id":"2503.17577","repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-layer-wise-analysis-of-ssl","title":"Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection","date":"2025-02-05","arxiv_id":"2502.03559","repositories_listed":1,"syntology":null},{"url":"/paper/neural-codec-source-tracing-toward","title":"Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition","date":"2025-01-11","arxiv_id":"2501.06514","repositories_listed":1,"syntology":null},{"url":"/paper/region-based-optimization-in-continual","title":"Region-Based Optimization in Continual Learning for Audio Deepfake Detection","date":"2024-12-16","arxiv_id":"2412.11551","repositories_listed":1,"syntology":null},{"url":"/paper/xlsr-mamba-a-dual-column-bidirectional-state","title":"XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection","date":"2024-11-15","arxiv_id":"2411.10027","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-tuning-for-audio-deepfake-detection","title":"Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset","date":"2024-10-13","arxiv_id":"2410.09869","repositories_listed":1,"syntology":null},{"url":"/paper/sonar-a-synthetic-ai-audio-detection","title":"Where are we in audio deepfake detection? A systematic analysis over generative and detection models","date":"2024-10-06","arxiv_id":"2410.04324","repositories_listed":1,"syntology":null},{"url":"/paper/safeear-content-privacy-preserving-audio","title":"SafeEar: Content Privacy-Preserving Audio Deepfake Detection","date":"2024-09-14","arxiv_id":"2409.09272","repositories_listed":1,"syntology":null},{"url":"/paper/does-current-deepfake-audio-detection-model","title":"Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?","date":"2024-08-20","arxiv_id":"2408.10853","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-channel-modeling-in-multi-head-self","title":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","date":"2024-06-25","arxiv_id":"2406.17376","repositories_listed":1,"syntology":null},{"url":"/paper/one-class-learning-with-adaptive-centroid","title":"One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection","date":"2024-06-24","arxiv_id":"2406.16716","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-source-tracing-detecting-novel","title":"Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy","date":"2024-06-05","arxiv_id":"2406.03240","repositories_listed":1,"syntology":null},{"url":"/paper/the-codecfake-dataset-and-countermeasures-for","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","date":"2024-05-08","arxiv_id":"2405.04880","repositories_listed":1,"syntology":null},{"url":"/paper/clad-robust-audio-deepfake-detection-against","title":"CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning","date":"2024-04-24","arxiv_id":"2404.15854","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneity-over-homogeneity-investigating","title":"Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake","date":"2024-03-31","arxiv_id":"2404.00809","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-green-ai-for-audio-deepfake","title":"Exploring Green AI for Audio Deepfake Detection","date":"2024-03-21","arxiv_id":"2403.14290","repositories_listed":1,"syntology":null},{"url":"/paper/what-to-remember-self-adaptive-continual","title":"What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection","date":"2023-12-15","arxiv_id":"2312.09651","repositories_listed":1,"syntology":null},{"url":"/paper/hm-conformer-a-conformer-based-audio-deepfake","title":"HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods","date":"2023-09-15","arxiv_id":"2309.08208","repositories_listed":1,"syntology":null},{"url":"/paper/fsd-an-initial-chinese-dataset-for-fake-song","title":"FSD: An Initial Chinese Dataset for Fake Song Detection","date":"2023-09-05","arxiv_id":"2309.02232","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/betray-oneself-a-novel-audio-deepfake","title":"Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion","date":"2023-05-25","arxiv_id":"2305.16353","repositories_listed":1,"syntology":null},{"url":"/paper/bts-e-audio-deepfake-detection-using","title":"Bts-e: Audio deepfake detection using breathing-talking-silence encoder","date":"2023-05-05","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}