{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:51:09Z","timestamp":1771519869940,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,10]]},"DOI":"10.1145\/3579856.3595801","type":"proceedings-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T14:52:13Z","timestamp":1688568733000},"page":"608-622","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Deepfake CAPTCHA: A Method for Preventing Fake Calls"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3075-8176","authenticated-orcid":false,"given":"Lior","family":"Yasur","sequence":"first","affiliation":[{"name":"Ben-Gurion University, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5559-5602","authenticated-orcid":false,"given":"Guy","family":"Frankovits","sequence":"additional","affiliation":[{"name":"Ben-Gurion University, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1652-7614","authenticated-orcid":false,"given":"Fred M.","family":"Grabovski","sequence":"additional","affiliation":[{"name":"Ben-Gurion University, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6367-2734","authenticated-orcid":false,"given":"Yisroel","family":"Mirsky","sequence":"additional","affiliation":[{"name":"Ben-Gurion University, Israel"}]}],"member":"320","published-online":{"date-parts":[[2023,7,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-39200-9_18"},{"key":"e_1_3_2_1_3_1","volume-title":"A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions. Algorithms 15, 5","author":"Almutairi Zaynab","year":"2022","unstructured":"Zaynab Almutairi and Hebah Elgibreen . 2022. A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions. Algorithms 15, 5 ( 2022 ). Zaynab Almutairi and Hebah Elgibreen. 2022. A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions. Algorithms 15, 5 (2022)."},{"key":"e_1_3_2_1_4_1","unstructured":"Kyle Alspach. 2022. AI-generated voice deepfakes see growing use in cyberattacks - Protocol. https:\/\/www.protocol.com\/enterprise\/deepfake-voice-cyberattack-ai-audio. (Accessed on 12\/15\/2022).  Kyle Alspach. 2022. AI-generated voice deepfakes see growing use in cyberattacks - Protocol. https:\/\/www.protocol.com\/enterprise\/deepfake-voice-cyberattack-ai-audio. (Accessed on 12\/15\/2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Voice spoofing countermeasure for logical access attacks detection","author":"Arif Tuba","year":"2021","unstructured":"Tuba Arif , Ali Javed , Mohammed Alhameed , Fathe Jeribi , and Ali Tahir . 2021. Voice spoofing countermeasure for logical access attacks detection . IEEE Access 9 ( 2021 ). Tuba Arif, Ali Javed, Mohammed Alhameed, Fathe Jeribi, and Ali Tahir. 2021. Voice spoofing countermeasure for logical access attacks detection. IEEE Access 9 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. CoRR abs\/2006.11477","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski , Henry Zhou , Abdelrahman Mohamed , and Michael Auli . 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. CoRR abs\/2006.11477 ( 2020 ). arXiv:2006.11477https:\/\/arxiv.org\/abs\/2006.11477 Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. CoRR abs\/2006.11477 (2020). arXiv:2006.11477https:\/\/arxiv.org\/abs\/2006.11477"},{"key":"e_1_3_2_1_7_1","first-page":"273","article-title":"Frequency domain-based detection of generated audio","volume":"2021","author":"Bartusiak R","year":"2021","unstructured":"Emily\u00a0 R Bartusiak and Edward\u00a0 J Delp . 2021 . Frequency domain-based detection of generated audio . Electronic Imaging 2021 , 4 (2021), 273 \u2013 271 . Emily\u00a0R Bartusiak and Edward\u00a0J Delp. 2021. Frequency domain-based detection of generated audio. Electronic Imaging 2021, 4 (2021), 273\u20131.","journal-title":"Electronic Imaging"},{"key":"e_1_3_2_1_8_1","volume-title":"Shamook: Star Wars effects company ILM hires Mandalorian deepfaker. https:\/\/www.bbc.com\/news\/entertainment-arts-57996094. (Acc. 12\/22).","author":"BBC.","year":"2021","unstructured":"BBC. 2021 . Shamook: Star Wars effects company ILM hires Mandalorian deepfaker. https:\/\/www.bbc.com\/news\/entertainment-arts-57996094. (Acc. 12\/22). BBC. 2021. Shamook: Star Wars effects company ILM hires Mandalorian deepfaker. https:\/\/www.bbc.com\/news\/entertainment-arts-57996094. (Acc. 12\/22)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"e_1_3_2_1_10_1","unstructured":"Thomas Brewster. 2021. Fraudsters Cloned Company Director\u2019s Voice In $35 Million Bank Heist Police Find. https:\/\/www.forbes.com\/sites\/thomasbrewster\/2021\/10\/14\/huge-bank-fraud-uses-deep-fake-voice-tech-to-steal-millions\/?sh=5bbb848d7559. (Accessed on 11\/27\/2022).  Thomas Brewster. 2021. Fraudsters Cloned Company Director\u2019s Voice In $35 Million Bank Heist Police Find. https:\/\/www.forbes.com\/sites\/thomasbrewster\/2021\/10\/14\/huge-bank-fraud-uses-deep-fake-voice-tech-to-steal-millions\/?sh=5bbb848d7559. (Accessed on 11\/27\/2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Workshop on Engineering Applications. Springer.","author":"\u00a0al Steven","year":"2021","unstructured":"Steven et \u00a0al . Camacho. 2021 . Fake speech recognition using deep learning . In Workshop on Engineering Applications. Springer. Steven et\u00a0al. Camacho. 2021. Fake speech recognition using deep learning. In Workshop on Engineering Applications. Springer."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00337"},{"key":"#cr-split#-e_1_3_2_1_13_1.1","doi-asserted-by":"crossref","unstructured":"Ju-chieh Chou Cheng-chieh Yeh and Hung-yi Lee. 2019. One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization. https:\/\/doi.org\/10.48550\/ARXIV.1904.05742 10.48550\/ARXIV.1904.05742","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"#cr-split#-e_1_3_2_1_13_1.2","doi-asserted-by":"crossref","unstructured":"Ju-chieh Chou Cheng-chieh Yeh and Hung-yi Lee. 2019. One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization. https:\/\/doi.org\/10.48550\/ARXIV.1904.05742","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"e_1_3_2_1_14_1","volume-title":"Megaportraits: One-shot megapixel neural head avatars. arXiv preprint arXiv:2207.07621","author":"Drobyshev Nikita","year":"2022","unstructured":"Nikita Drobyshev , Jenya Chelishev , Taras Khakhulin , Aleksei Ivakhnenko , Victor Lempitsky , and Egor Zakharov . 2022 . Megaportraits: One-shot megapixel neural head avatars. arXiv preprint arXiv:2207.07621 (2022). Nikita Drobyshev, Jenya Chelishev, Taras Khakhulin, Aleksei Ivakhnenko, Victor Lempitsky, and Egor Zakharov. 2022. Megaportraits: One-shot megapixel neural head avatars. arXiv preprint arXiv:2207.07621 (2022)."},{"key":"e_1_3_2_1_15_1","unstructured":"FBI. 2022. Internet Crime Complaint Center (IC3) | Deepfakes and Stolen PII Utilized to Apply for Remote Work Positions. https:\/\/www.ic3.gov\/Media\/Y2022\/PSA220628. (Accessed on 11\/30\/2022).  FBI. 2022. Internet Crime Complaint Center (IC3) | Deepfakes and Stolen PII Utilized to Apply for Remote Work Positions. https:\/\/www.ic3.gov\/Media\/Y2022\/PSA220628. (Accessed on 11\/30\/2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Raw differentiable architecture search for speech deepfake and spoofing detection. arXiv preprint arXiv:2107.12212","author":"Ge Wanying","year":"2021","unstructured":"Wanying Ge , Jose Patino , Massimiliano Todisco , and Nicholas Evans . 2021. Raw differentiable architecture search for speech deepfake and spoofing detection. arXiv preprint arXiv:2107.12212 ( 2021 ). Wanying Ge, Jose Patino, Massimiliano Todisco, and Nicholas Evans. 2021. Raw differentiable architecture search for speech deepfake and spoofing detection. arXiv preprint arXiv:2107.12212 (2021)."},{"key":"#cr-split#-e_1_3_2_1_17_1.1","unstructured":"Yewei Gu Zhenyu Zhang Xiaowei Yi and Xianfeng Zhao. 2021. MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features. https:\/\/doi.org\/10.48550\/ARXIV.2110.02500 10.48550\/ARXIV.2110.02500"},{"key":"#cr-split#-e_1_3_2_1_17_1.2","unstructured":"Yewei Gu Zhenyu Zhang Xiaowei Yi and Xianfeng Zhao. 2021. MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features. https:\/\/doi.org\/10.48550\/ARXIV.2110.02500"},{"key":"e_1_3_2_1_18_1","unstructured":"Karen Hao. 2021. Deepfake porn is ruining women\u2019s lives. Now the law may finally ban it. | MIT Technology Review. https:\/\/www.technologyreview.com\/2021\/02\/12\/1018222\/deepfake-revenge-porn-coming-ban\/. (Accessed on 12\/15\/2022).  Karen Hao. 2021. Deepfake porn is ruining women\u2019s lives. Now the law may finally ban it. | MIT Technology Review. https:\/\/www.technologyreview.com\/2021\/02\/12\/1018222\/deepfake-revenge-porn-coming-ban\/. (Accessed on 12\/15\/2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"#cr-split#-e_1_3_2_1_20_1.1","doi-asserted-by":"crossref","unstructured":"Takuhiro Kaneko Hirokazu Kameoka Kou Tanaka and Nobukatsu Hojo. 2020. CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion. https:\/\/doi.org\/10.48550\/ARXIV.2010.11672 10.48550\/ARXIV.2010.11672","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"#cr-split#-e_1_3_2_1_20_1.2","doi-asserted-by":"crossref","unstructured":"Takuhiro Kaneko Hirokazu Kameoka Kou Tanaka and Nobukatsu Hojo. 2020. CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion. https:\/\/doi.org\/10.48550\/ARXIV.2010.11672","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"e_1_3_2_1_21_1","volume-title":"Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection. arXiv","author":"Kawa Piotr","year":"2022","unstructured":"Piotr Kawa , Marcin Plata , and Piotr Syga . 2022. Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection. arXiv ( 2022 ). Piotr Kawa, Marcin Plata, and Piotr Syga. 2022. Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection. arXiv (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection. arXiv preprint","author":"Kawa Piotr","year":"2022","unstructured":"Piotr Kawa , Marcin Plata , and Piotr Syga . 2022. SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection. arXiv preprint ( 2022 ). Piotr Kawa, Marcin Plata, and Piotr Syga. 2022. SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection. arXiv preprint (2022)."},{"key":"e_1_3_2_1_23_1","unstructured":"Bryan Ke. 2022. Singaporean man\u2019s face ends up in deepfake porn after he refuses to pay hacker $5 800. https:\/\/news.yahoo.com\/singaporean-mans-face-ends-deepfake-171743924.html. (Accessed on 11\/27\/2022).  Bryan Ke. 2022. Singaporean man\u2019s face ends up in deepfake porn after he refuses to pay hacker $5 800. https:\/\/news.yahoo.com\/singaporean-mans-face-ends-deepfake-171743924.html. (Accessed on 11\/27\/2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476099.3484315"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00336"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-06297-w"},{"key":"#cr-split#-e_1_3_2_1_27_1.1","unstructured":"Kang-wook Kim Seung-won Park Junhyeok Lee and Myun-chul Joe. 2021. Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques. https:\/\/doi.org\/10.48550\/ARXIV.2104.00931 10.48550\/ARXIV.2104.00931"},{"key":"#cr-split#-e_1_3_2_1_27_1.2","unstructured":"Kang-wook Kim Seung-won Park Junhyeok Lee and Myun-chul Joe. 2021. Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques. https:\/\/doi.org\/10.48550\/ARXIV.2104.00931"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.099"},{"key":"e_1_3_2_1_29_1","unstructured":"Dami Lee. 2019. Deepfake Salvador Dal\u00ed takes selfies with museum visitors - The Verge. https:\/\/www.theverge.com\/2019\/5\/10\/18540953\/salvador-dali-lives-deepfake-museum. (Accessed on 12\/15\/2022).  Dami Lee. 2019. Deepfake Salvador Dal\u00ed takes selfies with museum visitors - The Verge. https:\/\/www.theverge.com\/2019\/5\/10\/18540953\/salvador-dali-lives-deepfake-museum. (Accessed on 12\/15\/2022)."},{"key":"e_1_3_2_1_30_1","unstructured":"Zhenchun Lei Yingen Yang Changhong Liu and Jihua Ye. 2020. Siamese Convolutional Neural Network Using Gaussian Probability Feature for Spoofing Speech Detection.. In INTERSPEECH. 1116\u20131120.  Zhenchun Lei Yingen Yang Changhong Liu and Jihua Ye. 2020. Siamese Convolutional Neural Network Using Gaussian Probability Feature for Spoofing Speech Detection.. In INTERSPEECH. 1116\u20131120."},{"key":"e_1_3_2_1_31_1","unstructured":"Marlene Lenthang. 2021. Cheerleader\u2019s mom created deepfake videos to allegedly harass her daughter\u2019s rivals. https:\/\/abcnews.go.com\/US\/cheerleaders-mom-created-deepfake-videos-allegedly-harass-daughters\/story?id=76437596. (Accessed on 12\/15\/2022).  Marlene Lenthang. 2021. Cheerleader\u2019s mom created deepfake videos to allegedly harass her daughter\u2019s rivals. https:\/\/abcnews.go.com\/US\/cheerleaders-mom-created-deepfake-videos-allegedly-harass-daughters\/story?id=76437596. (Accessed on 12\/15\/2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion. CoRR abs\/2107.10394","author":"Li Yinghao\u00a0Aaron","year":"2021","unstructured":"Yinghao\u00a0Aaron Li , Ali Zare , and Nima Mesgarani . 2021. StarGANv2-VC : A Diverse , Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion. CoRR abs\/2107.10394 ( 2021 ). arXiv:2107.10394https:\/\/arxiv.org\/abs\/2107.10394 Yinghao\u00a0Aaron Li, Ali Zare, and Nima Mesgarani. 2021. StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion. CoRR abs\/2107.10394 (2021). arXiv:2107.10394https:\/\/arxiv.org\/abs\/2107.10394"},{"key":"#cr-split#-e_1_3_2_1_33_1.1","unstructured":"Yist\u00a0Y. Lin Chung-Ming Chien Jheng-Hao Lin Hung-yi Lee and Lin-shan Lee. 2020. FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention. https:\/\/doi.org\/10.48550\/ARXIV.2010.14150 10.48550\/ARXIV.2010.14150"},{"key":"#cr-split#-e_1_3_2_1_33_1.2","unstructured":"Yist\u00a0Y. Lin Chung-Ming Chien Jheng-Hao Lin Hung-yi Lee and Lin-shan Lee. 2020. FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention. https:\/\/doi.org\/10.48550\/ARXIV.2010.14150"},{"key":"e_1_3_2_1_34_1","volume-title":"Identification of fake stereo audio using SVM and CNN. Information 12, 7","author":"Liu Tianyun","year":"2021","unstructured":"Tianyun Liu , Diqun Yan , Rangding Wang , Nan Yan , and Gang Chen . 2021. Identification of fake stereo audio using SVM and CNN. Information 12, 7 ( 2021 ). Tianyun Liu, Diqun Yan, Rangding Wang, Nan Yan, and Gang Chen. 2021. Identification of fake stereo audio using SVM and CNN. Information 12, 7 (2021)."},{"key":"e_1_3_2_1_35_1","volume-title":"Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward. Applied Intelligence","author":"Masood Momina","year":"2022","unstructured":"Momina Masood , Mariam Nawaz , Khalid\u00a0Mahmood Malik , Ali Javed , Aun Irtaza , and Hafiz Malik . 2022. Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward. Applied Intelligence ( 2022 ), 1\u201353. Momina Masood, Mariam Nawaz, Khalid\u00a0Mahmood Malik, Ali Javed, Aun Irtaza, and Hafiz Malik. 2022. Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward. Applied Intelligence (2022), 1\u201353."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101096"},{"key":"e_1_3_2_1_38_1","volume-title":"Does Audio Deepfake Detection Generalize?arXiv preprint arXiv:2203.16263","author":"M\u00fcller M","year":"2022","unstructured":"Nicolas\u00a0 M M\u00fcller , Pavel Czempin , Franziska Dieckmann , Adam Froghyar , and Konstantin B\u00f6ttinger . 2022. Does Audio Deepfake Detection Generalize?arXiv preprint arXiv:2203.16263 ( 2022 ). Nicolas\u00a0M M\u00fcller, Pavel Czempin, Franziska Dieckmann, Adam Froghyar, and Konstantin B\u00f6ttinger. 2022. Does Audio Deepfake Detection Generalize?arXiv preprint arXiv:2203.16263 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Deepfake audio detection by speaker verification. arXiv preprint","author":"Pianese Alessandro","year":"2022","unstructured":"Alessandro Pianese , Davide Cozzolino , Giovanni Poggi , and Luisa Verdoliva . 2022. Deepfake audio detection by speaker verification. arXiv preprint ( 2022 ). Alessandro Pianese, Davide Cozzolino, Giovanni Poggi, and Luisa Verdoliva. 2022. Deepfake audio detection by speaker verification. arXiv preprint (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. https:\/\/doi.org\/10","author":"Qian Kaizhi","year":"2020","unstructured":"Kaizhi Qian , Zeyu Jin , Mark Hasegawa-Johnson , and Gautham\u00a0 J. Mysore . 2020 . F0-Consistent Many-To-Many Non-Parallel Voice Conversion Via Conditional Autoencoder . In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. https:\/\/doi.org\/10 .1109\/icassp40776.2020.9054734 10.1109\/icassp40776.2020.9054734 Kaizhi Qian, Zeyu Jin, Mark Hasegawa-Johnson, and Gautham\u00a0J. Mysore. 2020. F0-Consistent Many-To-Many Non-Parallel Voice Conversion Via Conditional Autoencoder. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. https:\/\/doi.org\/10.1109\/icassp40776.2020.9054734"},{"key":"e_1_3_2_1_41_1","volume-title":"SpeechBrain: A general-purpose speech toolkit. arXiv preprint arXiv:2106.04624","author":"Ravanelli Mirco","year":"2021","unstructured":"Mirco Ravanelli , Titouan Parcollet , Peter Plantinga , Aku Rouhe , Samuele Cornell , Loren Lugosch , Cem Subakan , Nauman Dawalatabad , Abdelwahab Heba , Jianyuan Zhong , 2021. SpeechBrain: A general-purpose speech toolkit. arXiv preprint arXiv:2106.04624 ( 2021 ). Mirco Ravanelli, Titouan Parcollet, Peter Plantinga, Aku Rouhe, Samuele Cornell, Loren Lugosch, Cem Subakan, Nauman Dawalatabad, Abdelwahab Heba, Jianyuan Zhong, 2021. SpeechBrain: A general-purpose speech toolkit. arXiv preprint arXiv:2106.04624 (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Convoice: Real-time zero-shot voice style transfer with convolutional network. arXiv preprint arXiv:2005.07815","author":"Rebryk Yurii","year":"2020","unstructured":"Yurii Rebryk and Stanislav Beliaev . 2020 . Convoice: Real-time zero-shot voice style transfer with convolutional network. arXiv preprint arXiv:2005.07815 (2020). Yurii Rebryk and Stanislav Beliaev. 2020. Convoice: Real-time zero-shot voice style transfer with convolutional network. arXiv preprint arXiv:2005.07815 (2020)."},{"key":"e_1_3_2_1_43_1","unstructured":"ReSpeecher. 2022. Voice Cloning Software for Content Creators | Respeecher. https:\/\/www.respeecher.com\/. (Accessed on 12\/15\/2022).  ReSpeecher. 2022. Voice Cloning Software for Content Creators | Respeecher. https:\/\/www.respeecher.com\/. (Accessed on 12\/15\/2022)."},{"key":"e_1_3_2_1_44_1","unstructured":"Andrew Roth. 2021. European MPs targeted by deepfake video calls. https:\/\/www.theguardian.com\/world\/2021\/apr\/22\/european-mps-targeted-by-deepfake-video-calls-imitating-russian-opposition. (Accessed on 11\/27\/2022).  Andrew Roth. 2021. European MPs targeted by deepfake video calls. https:\/\/www.theguardian.com\/world\/2021\/apr\/22\/european-mps-targeted-by-deepfake-video-calls-imitating-russian-opposition. (Accessed on 11\/27\/2022)."},{"key":"e_1_3_2_1_45_1","volume-title":"A Cross-Verification Approach for Protecting World Leaders from Fake and Tampered Audio. arXiv preprint","author":"Shan Mengyi","year":"2020","unstructured":"Mengyi Shan and TJ Tsai . 2020. A Cross-Verification Approach for Protecting World Leaders from Fake and Tampered Audio. arXiv preprint ( 2020 ). Mengyi Shan and TJ Tsai. 2020. A Cross-Verification Approach for Protecting World Leaders from Fake and Tampered Audio. arXiv preprint (2020)."},{"key":"e_1_3_2_1_46_1","volume-title":"Advances in Neural Information Processing Systems 32. Curran Associates","author":"Siarohin Aliaksandr","unstructured":"Aliaksandr Siarohin , St\u00e9phane Lathuili\u00e8re , Sergey Tulyakov , Elisa Ricci , and Nicu Sebe . 2019. First Order Motion Model for Image Animation . In Advances in Neural Information Processing Systems 32. Curran Associates , Inc ., 7135\u20137145. http:\/\/papers.nips.cc\/paper\/8935-first-order-motion-model-for-image-animation.pdf Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First Order Motion Model for Image Animation. In Advances in Neural Information Processing Systems 32. Curran Associates, Inc., 7135\u20137145. http:\/\/papers.nips.cc\/paper\/8935-first-order-motion-model-for-image-animation.pdf"},{"key":"e_1_3_2_1_47_1","unstructured":"Catherine Stupp. 2019. Fraudsters Used AI to Mimic CEO\u2019s Voice in Unusual Cybercrime Case - WSJ. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-to-mimic-ceos-voice-in-unusual-cybercrime-case-11567157402. (Accessed on 11\/27\/2022).  Catherine Stupp. 2019. Fraudsters Used AI to Mimic CEO\u2019s Voice in Unusual Cybercrime Case - WSJ. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-to-mimic-ceos-voice-in-unusual-cybercrime-case-11567157402. (Accessed on 11\/27\/2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection. arXiv preprint arXiv:2107.12710","author":"Tak Hemlata","year":"2021","unstructured":"Hemlata Tak , Jee-weon Jung, Jose Patino , Madhu Kamble , Massimiliano Todisco , and Nicholas Evans . 2021. End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection. arXiv preprint arXiv:2107.12710 ( 2021 ). Hemlata Tak, Jee-weon Jung, Jose Patino, Madhu Kamble, Massimiliano Todisco, and Nicholas Evans. 2021. End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection. arXiv preprint arXiv:2107.12710 (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1097\/00003446-199204000-00002","article-title":"Processing the telephone speech signal for the hearing impaired","volume":"13","author":"Terry Mark","year":"1992","unstructured":"Mark Terry , Kathryn Bright , Mike Durian , Laura Kepler , Richard Sweetman , and Michael Grim . 1992 . Processing the telephone speech signal for the hearing impaired . Ear and Hearing 13 , 2 (1992), 70 \u2013 79 . Mark Terry, Kathryn Bright, Mike Durian, Laura Kepler, Richard Sweetman, and Michael Grim. 1992. Processing the telephone speech signal for the hearing impaired. Ear and Hearing 13, 2 (1992), 70\u201379.","journal-title":"Ear and Hearing"},{"key":"e_1_3_2_1_51_1","volume-title":"ASVspoof 2019: Future horizons in spoofed and fake audio detection. arXiv preprint arXiv:1904.05441","author":"Todisco Massimiliano","year":"2019","unstructured":"Massimiliano Todisco , Xin Wang , Ville Vestman , Md Sahidullah , H\u00e9ctor Delgado , Andreas Nautsch , Junichi Yamagishi , Nicholas Evans , Tomi Kinnunen , and Kong\u00a0Aik Lee . 2019. ASVspoof 2019: Future horizons in spoofed and fake audio detection. arXiv preprint arXiv:1904.05441 ( 2019 ). Massimiliano Todisco, Xin Wang, Ville Vestman, Md Sahidullah, H\u00e9ctor Delgado, Andreas Nautsch, Junichi Yamagishi, Nicholas Evans, Tomi Kinnunen, and Kong\u00a0Aik Lee. 2019. ASVspoof 2019: Future horizons in spoofed and fake audio detection. arXiv preprint arXiv:1904.05441 (2019)."},{"key":"e_1_3_2_1_52_1","volume-title":"Irfan Essa, and Wenke Lee.","author":"Uzun Erkam","year":"2018","unstructured":"Erkam Uzun , Simon Pak\u00a0Ho Chung , Irfan Essa, and Wenke Lee. 2018 . rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System.. In NDSS. Erkam Uzun, Simon Pak\u00a0Ho Chung, Irfan Essa, and Wenke Lee. 2018. rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System.. In NDSS."},{"key":"e_1_3_2_1_53_1","unstructured":"Jai Vijayan. 2022. Reshaping the Threat Landscape: Deepfake Cyberattacks Are Here. https:\/\/www.darkreading.com\/threat-intelligence\/threat-landscape-deepfake-cyberattacks-are-here. (Accessed on 12\/15\/2022).  Jai Vijayan. 2022. Reshaping the Threat Landscape: Deepfake Cyberattacks Are Here. https:\/\/www.darkreading.com\/threat-intelligence\/threat-landscape-deepfake-cyberattacks-are-here. (Accessed on 12\/15\/2022)."},{"key":"e_1_3_2_1_54_1","unstructured":"James Vincent. 2022. Binance executive claims scammers made a deepfake of him - The Verge. https:\/\/www.theverge.com\/2022\/8\/23\/23318053\/binance-comms-crypto-chief-deepfake-scam-claim-patrick-hillmann. (Accessed on 11\/27\/2022).  James Vincent. 2022. Binance executive claims scammers made a deepfake of him - The Verge. https:\/\/www.theverge.com\/2022\/8\/23\/23318053\/binance-comms-crypto-chief-deepfake-scam-claim-patrick-hillmann. (Accessed on 11\/27\/2022)."},{"key":"e_1_3_2_1_55_1","unstructured":"Jane Wakefield. 2022. Deepfake presidents used in Russia-Ukraine war - BBC News. https:\/\/www.bbc.com\/news\/technology-60780142. (Accessed on 11\/27\/2022).  Jane Wakefield. 2022. Deepfake presidents used in Russia-Ukraine war - BBC News. https:\/\/www.bbc.com\/news\/technology-60780142. (Accessed on 11\/27\/2022)."},{"key":"e_1_3_2_1_56_1","volume-title":"2020 2nd International Conference on Advancements in Computing (ICAC), Vol.\u00a01. IEEE, 192\u2013197","author":"Wijethunga RLMAPC","year":"2020","unstructured":"RLMAPC Wijethunga , DMK Matheesha , Abdullah Al\u00a0Noman , KHVTA De\u00a0Silva , Muditha Tissera , and Lakmal Rupasinghe . 2020 . Deepfake audio detection: a deep learning based solution for group conversations . In 2020 2nd International Conference on Advancements in Computing (ICAC), Vol.\u00a01. IEEE, 192\u2013197 . RLMAPC Wijethunga, DMK Matheesha, Abdullah Al\u00a0Noman, KHVTA De\u00a0Silva, Muditha Tissera, and Lakmal Rupasinghe. 2020. Deepfake audio detection: a deep learning based solution for group conversations. In 2020 2nd International Conference on Advancements in Computing (ICAC), Vol.\u00a01. IEEE, 192\u2013197."},{"key":"e_1_3_2_1_57_1","volume-title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. arXiv preprint arXiv:2109.00537","author":"Yamagishi Junichi","year":"2021","unstructured":"Junichi Yamagishi , Xin Wang , Massimiliano Todisco , Md Sahidullah , Jose Patino , Andreas Nautsch , Xuechen Liu , Kong\u00a0Aik Lee , Tomi Kinnunen , Nicholas Evans , 2021. ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. arXiv preprint arXiv:2109.00537 ( 2021 ). Junichi Yamagishi, Xin Wang, Massimiliano Todisco, Md Sahidullah, Jose Patino, Andreas Nautsch, Xuechen Liu, Kong\u00a0Aik Lee, Tomi Kinnunen, Nicholas Evans, 2021. ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. arXiv preprint arXiv:2109.00537 (2021)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"}],"event":{"name":"ASIA CCS '23: ACM ASIA Conference on Computer and Communications Security","location":"Melbourne VIC Australia","acronym":"ASIA CCS '23","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the ACM Asia Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579856.3595801","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:17Z","timestamp":1750183697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579856.3595801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":63,"alternative-id":["10.1145\/3579856.3595801","10.1145\/3579856"],"URL":"https:\/\/doi.org\/10.1145\/3579856.3595801","relation":{},"subject":[],"published":{"date-parts":[[2023,7,10]]},"assertion":[{"value":"2023-07-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}