Synthesizing voice with the help of machine learning techniques has made rapid progress over the last years [1] and first high profile fraud cases have been recently reported [2]. Given the current increase in using conferencing tools for online teaching, we question just how easy (i.e. needed data, hardware, skill set) it would be to create a convincing voice fake. We analyse how much training data a participant (e.g. a student) would actually need to fake another participants voice (e.g. a professor). We provide an analysis of the existing state of the art in creating voice deep fakes, as well as offer detailed technical guidance and evidence of just how much effort is needed to copy a voice. A user study with more than 100 participants shows how difficult it is to identify real and fake voice (on avg. only 37 percent can distinguish between real and fake voice of a professor). With a focus on German language and an online teaching environment we discuss the societal implications as well as demonstrate how to use machine learning techniques to possibly detect such fakes.
Textual Acoustic Grounding for Generalizable LLM-Based Deepfake Voice Detection
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；National Institute of Informatics（情报信息学研究所）；Technical University of Berlin（柏林工业大学）
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Columbia University（哥伦比亚大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；New York University（纽约大学）；Pennsylvania State University（宾夕法尼亚州立大学）；Rutgers University（罗格斯大学）
A Comprehensive Survey with Critical Analysis for Deepfake Speech Detection
Austrian Institute of Technology（奥地利技术研究院）；HCM University of Technology（胡志明市理工大学）；University of Technology of Troyes（特鲁瓦技术大学）；FPT University（FPT大学）；BLOOM Social Analytics（BLOOM社会分析公司）；Université de technologie de Compiègne（贡比涅技术大学）
What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Computer and Information Technology, University of Beijing Jiaotong（北京交通大学计算机与信息技术学院）；Department of Automation, Tsinghua University（清华大学自动化系）；University of Science and Technology of China（中国科学技术大学）
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 pa…
Mitigating Unauthorized Speech Synthesis for Voice Protection
Beijing University of Posts and Telecommunications（北京邮电大学）；CSIRO’s Data61（联邦科学与工业研究组织Data61）；National University of Singapore（新加坡国立大学）；The University of Hong Kong（香港大学）
D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack
School of Computer Science（计算机学院）；University College Dublin（都柏林大学学院）；School of Computer Science and Statistics（计算机与统计学院）；Trinity College Dublin（都柏林圣三一学院）；University of Science（科学大学）
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎-罗克琴克特研究所）；Rajiv Gandhi University（拉贾·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）；Department of Electrical, Computer and Biomedical Engineering（电气、计算机和生物医学工程系）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Shenzhen Key Laboratory of Ubiquitous Data Enabling（深圳无处不在数据赋能重点实验室）
The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work we present a novel approach for synthetic speech detection, exploiting the combination of two high-level semantic properties of the human voice. On one side, we focus on speaker identity cues and represent them as speaker embeddings extracted using a state-of-the-art method for the automatic speaker verification task. On the other side, voice prosody, intende…
Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools are possible and likely, posing a serious threat to our society. Hence, synthetic voice detection has become a pressing research topic, and a large variety of detection methods have been recently proposed. Unfortunately, they hardly generalize to synthetic audios generated by tools never seen in the training phase, which makes them unfit to face real-world scenarios. In this work, we aim at overcoming this issue by …
Hindi audio-video-Deepfake (HAV-DF): A Hindi language-based Audio-video Deepfake Dataset
BML Munjal University（BML蒙贾尔大学）；School of Engineering & Technology, BML Munjal University（BML蒙贾尔大学工程与技术学院）；Center for Advanced Data and Computational Science, BML Munjal University（BML蒙贾尔大学高级数据与计算科学中心）
