Despite several years of research in deepfake and spoofing detection for automatic speaker verification, little is known about the artefacts that classifiers use to distinguish between bona fide and spoofed utterances. An understanding of these is crucial to the design of trustworthy, explainable solutions. In this paper we report an extension of our previous work to better understand classifier behaviour to the use of SHapley Additive exPlanations (SHAP) to attack analysis. Our goal is to identify the artefacts that characterise utterances generated by different attacks algorithms. Using a pair of classifiers which operate either upon raw waveforms or magnitude spectrograms, we show that visualisations of SHAP results can be used to identify attack-specific artefacts and the differences and consistencies between synthetic speech and converted voice spoofing attacks.
Towards Scalable AASIST: Refining Graph Attention for Speech Deepfake Detection
Speechka.ai Information Technologies, Mechanics and Optics University（Speechka.ai 信息科技，力学与光学大学）；St. Petersburg State University（圣彼得堡州立大学）；Moscow Technical University of Communications and Informatics（莫斯科通信与信息学技术大学）
EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection
School of Cyber Science and Engineering, Wuhan University（武汉大学网络安全科学与工程学院）；Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education（教育部航空航天信息安全与可信计算重点实验室）
Profiling the Voice: Speaker-Specific Phoneme Fingerprinting for Speech Deepfake Detection
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education（航空航天信息安全与可信计算重点实验室，教育部）；School of Cyber Science and Engineering, Wuhan University（武汉大学计算机科学与工程学院）
SpoofCeleb: Speech Deepfake Detection and SASV In The Wild
Carnegie Mellon University（卡内基梅隆大学）；Renmin University of China（中国人民大学）；National Institute of Informatics（信息学研究所）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Meta；University of Tokyo（东京大学）；EURECOM（欧洲通信学院）；Shanghai Jiao Tong University（上海交通大学）；Yonsei University（延世大学）；Keio University（庆应义塾大学）
Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou, China（信息与电子工程学院，浙江工商大学，杭州，中国）；Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, USA（电气与计算机工程系，新泽西理工学院，纽卡斯尔，美国）
AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
Communication University of China（中国传媒大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Institute of Technology（北京理工大学）；Shanghai Jiao Tong University（上海交通大学）
Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection
School of Computer Science and Technology, Xinjiang University, Urumqi, China（新疆大学计算机科学与技术学院）；Hefei iFly Digital Technology Co. Ltd., Hefei, China（合肥iFly数字技术有限公司）；University of Science and Technology of China, Hefei, China（中国科学技术大学）；Department of Electronic Engineering, Tsinghua University, Beijing, China（清华大学电子工程系）
Institute for Advancing Intelligence, TCG Centres for Research and Education in Science and Technology（TCG科学与技术研究教育中心智能推进研究所）；Indian Statistical Institute, Kolkata（印度统计研究所）；Academy of Scientific and Innovative Research (AcSIR)（科学与创新研究院）
Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing
Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电子与计算机工程系）；LIGHTSPEED, Singapore（新加坡LIGHTSPEED公司）；Nanyang Technological University, Singapore（南洋理工大学）；Fortemedia Singapore, Singapore（新加坡Fortemedia公司）；Department of Electrical and Electronic Engineering and the Research Centre for Data Science & Artificial Intelligence, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系及数据科学与人工智能研究中心）；Shenzhen Research Institute of Big Data, School of Artificial Intelligence, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）大数据研究院、人工智能学院、数据科学学院）
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用实验室）；National Institute of Informatics（国立信息学研究所）；Institute for Advancing Intelligence, TCG CREST（TCG CREST 智能推进研究所）；EURECOM（欧洲通信学院）；Cerence Inc.（赛轮思公司）；Avignon Université（阿维尼翁大学）；Nuance Communications（Nuance 通信公司）；University of Eastern Finland（东芬兰大学）
Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection
Nanyang Technological University, Singapore（南洋理工大学，新加坡）；National University of Singapore, Singapore（国立新加坡大学，新加坡）；The Hong Kong Polytechnic University, Hong Kong（香港理工大学，香港）
