{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T14:48:15Z","timestamp":1777733295362,"version":"3.51.4"},"reference-count":38,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":118,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2025J01156"],"award-info":[{"award-number":["2025J01156"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZQN-1112"],"award-info":[{"award-number":["ZQN-1112"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>The advancement of deepfake technology has enabled deepfake audio to achieve unprecedented realism, posing significant challenges to automatic speaker verification (ASV) systems and threatening information security in critical sectors such as telecommunications and banking. As a countermeasure, Audio Deepfake Detection (ADD) has received growing attention in recent years. Existing ADD techniques derived from deep\u2010learning framework often encounter the problem of insufficient generalizability on unseen deepfake methods and insufficient robustness with changes to the codec and noise condition. To address these challenges, we propose an efficient method that adapts self\u2010supervised learning (SSL) model WavLM for deepfake detection. Instead of costly full\u2010model retraining, we introduce a lightweight \u201cadapter\u201d module, which acts as a small, trainable component to efficiently teach WavLM this new task. This adapter incorporates a Gaussian attention mechanism, which guides the model to consistently focus on subtle vocal artifacts and ignore irrelevant noise or compression distortions, thereby ensuring robust performance across different real\u2010world conditions. Extensive evaluations show that our framework not only achieves competitive performance on the ASVspoof 2019 LA and DF in\u2010domain benchmarks but, more importantly, excels in generalization. Our method achieves EERs of 6.11% on the challenging \u2018in\u2010the\u2010wild\u2019 dataset and 4.90% on the WaveFake dataset, outperforming existing methods against previously unseen deepfake attacks. This superior generalization is further explained through SHAP analysis, which reveals that our method enables the model to focus on discriminative information within voiced segments, effectively ignoring fragile \u2018shortcut\u2019 cues from silent portions that often hinder generalization in other systems.<\/jats:p>","DOI":"10.1155\/int\/6786731","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T11:07:19Z","timestamp":1777460839000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Gaussian Attention for Adapter\u2010Based Fine\u2010Tuning of WavLM in Audio Deepfake Detection"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8344-1497","authenticated-orcid":false,"given":"Yuhan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3120-8387","authenticated-orcid":false,"given":"Xiaodan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5352-1318","authenticated-orcid":false,"given":"Yingqiang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3749-5537","authenticated-orcid":false,"given":"Gewei","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"e_1_2_11_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3171974"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10539-8"},{"key":"e_1_2_11_4_2","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/978-981-19-5288-3_13","article-title":"Introduction to Voice Presentation Attack Detection and Recent Advances","author":"Sahidullah Md","year":"2023","journal-title":"Handbook of Biometric Anti-Spoofing: Presentation Attack Detection and Vulnerability Assessment"},{"key":"e_1_2_11_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13152947"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1520"},{"key":"e_1_2_11_7_2","article-title":"Cybersecurity, Digital Forensics, and the Iot for Deepfake Investigation on Social Media Platforms: A Review","volume":"15","author":"Ayub Khan A.","year":"2025","journal-title":"Human-Centric Computing and Information Sciences"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-024-10255-7"},{"key":"e_1_2_11_9_2","doi-asserted-by":"crossref","first-page":"75","DOI":"10.21437\/ASVSPOOF.2021-12","volume-title":"2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge","author":"Chen X.","year":"2021"},{"key":"e_1_2_11_10_2","first-page":"6354","volume-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Li X.","year":"2021"},{"key":"e_1_2_11_11_2","doi-asserted-by":"crossref","DOI":"10.21437\/ASVSPOOF.2021-4","article-title":"Raw Differentiable Architecture Search for Speech Deepfake and Spoofing Detection","author":"Ge W.","year":"2021","journal-title":"Autom. Speaker Verification Spoofing Countermeasures Challenge"},{"key":"e_1_2_11_12_2","first-page":"6367","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Jung J.-weon","year":"2022"},{"key":"e_1_2_11_13_2","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-supervised Learning of Speech Representations","volume":"33","author":"Baevski A.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_14_2","first-page":"2278","volume-title":"Interspeech 2022","author":"Babu A.","year":"2021"},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"e_1_2_11_17_2","unstructured":"LinT.-Yi GoyalP. GirshickR. HeK. andDoll\u00e1rP. Focal Loss for Dense Object Detection Proceedings of the IEEE International Conference on Computer Vision 2017 Salt Lake City 2980\u20132988."},{"key":"e_1_2_11_18_2","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.52202\/068431-0116","article-title":"Adafocal: Calibration-Aware Adaptive Focal Loss","volume":"35","author":"Ghosh A.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"e_1_2_11_20_2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.21437\/ASVSPOOF.2021-8","volume-title":"2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge","author":"Yamagishi J.","year":"2021"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3285283"},{"key":"e_1_2_11_22_2","doi-asserted-by":"crossref","first-page":"2783","DOI":"10.21437\/Interspeech.2022-108","volume-title":"Interspeech 2022","author":"M\u00fcller N. M.","year":"2022"},{"key":"e_1_2_11_23_2","unstructured":"FrankJ.andSch\u00f6nherrL. Wavefake: A Data Set to Facilitate Audio Deepfake Detection Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 2021 NeurIPS Datasets and Benchmarks 1\u201317."},{"key":"e_1_2_11_24_2","first-page":"6387","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ge W.","year":"2022"},{"key":"e_1_2_11_25_2","first-page":"4765","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Scott M. L.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_26_2","doi-asserted-by":"crossref","first-page":"112","DOI":"10.21437\/Odyssey.2022-16","volume-title":"The Speaker and Language Recognition Workshop (Odyssey 2022)","author":"Tak H.","year":"2022"},{"key":"e_1_2_11_27_2","first-page":"12702","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"pan Y.","year":"2024"},{"key":"e_1_2_11_28_2","first-page":"10311","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Wang X.","year":"2024"},{"key":"e_1_2_11_29_2","doi-asserted-by":"crossref","first-page":"3844","DOI":"10.21437\/Interspeech.2023-1254","volume-title":"Interspeech 2023","author":"Wang C.","year":"2023"},{"key":"e_1_2_11_30_2","doi-asserted-by":"crossref","first-page":"2090","DOI":"10.21437\/Interspeech.2024-1472","volume-title":"Interspeech 2024","author":"Pan Z.","year":"2024"},{"key":"e_1_2_11_31_2","first-page":"67901","article-title":"Slim: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection","volume":"37","author":"Zhu Yi","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_32_2","first-page":"1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Wang X.","year":"2023"},{"key":"e_1_2_11_33_2","doi-asserted-by":"crossref","unstructured":"TakH. KambleM. PatinoJ. TodiscoM. andEvansN. Rawboost: A Raw Data Boosting and Augmentation Method Applied to Automatic Speaker Verification Anti-Spoofing ICASSP 2022-2022 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) 2022 Singapore IEEE 6382\u20136386.","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"e_1_2_11_34_2","first-page":"13131","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Yang Y.","year":"2024"},{"key":"e_1_2_11_35_2","first-page":"11251","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Lu J.","year":"2024"},{"key":"e_1_2_11_36_2","first-page":"4828","article-title":"Towards Generalisable and Calibrated Audio Deepfake Detection With Self-Supervised Representations","volume":"2024","author":"Pascu O.","year":"2024","journal-title":"Interspeech"},{"key":"e_1_2_11_37_2","doi-asserted-by":"crossref","unstructured":"ZhangQ. WenS. andHuT. Audio Deepfake Detection With Self-Supervised xls-r and Sls Classifier Proceedings of the 32nd ACM International Conference on Multimedia 2024 Melbourne Australia 6765\u20136773.","DOI":"10.1145\/3664647.3681345"},{"key":"e_1_2_11_38_2","doi-asserted-by":"crossref","first-page":"56","DOI":"10.21437\/SynData4GenAI.2024-12","volume-title":"Synthetic Data\u2019s Transformative Role in Foundational Speech Models","author":"Shim H.","year":"2024"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/6786731","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/6786731","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/6786731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T11:07:26Z","timestamp":1777460846000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/6786731"}},"subtitle":[],"editor":[{"given":"Kallol","family":"Mohanta","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/6786731"],"URL":"https:\/\/doi.org\/10.1155\/int\/6786731","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-07-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6786731"}}