Hung Dinh-Xuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hung Dinh-Xuan has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Souhwan Jung
Soongsil University, Seoul, Republic of Korea
4 shared publications - Thien-Phuc Doan
Soongsil University, Seoul, Republic of Korea
4 shared publications - Inho Kim
Soongsil University, Seoul, Republic of Korea
2 shared publications - Kihun Hong
Soongsil University
2 shared publications - SeongKyu Han
Soongsil University, Seoul, Republic of Korea
2 shared publications - Woongjae Lee
Soongsil University, Seoul, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 142078-142090
Early-Reflection Wiener Filter and Spectral Subtraction for Replay-Resilient Audio Deepfake Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 142078-142090
Open AccessEarly-Reflection Wiener Filter and Spectral Subtraction for Replay-Resilient Audio Deepfake Detection
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 44-51
Defending Speaker Verification Against Deepfake: A Multi-Step Approach
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 44-51
Open AccessDefending Speaker Verification Against Deepfake: A Multi-Step Approach
- 24 June 2025
- Published by Springer Nature
- p. 409-422
Towards Real-Time Audio Deepfake Detection in Resource-Limited Environments
- 24 June 2025
- Published by Springer Nature
- p. 409-422
Towards Real-Time Audio Deepfake Detection in Resource-Limited Environments
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2222-2235
Trident of Poseidon: A Generalized Approach for Detecting Deepfake Voices
Deepfakes, an increasingly prevalent form of information attack, pose serious threats to security and privacy. Deepfake voice attacks, in particular, have the potential to cause widespread disruption, creating an urgent need for an effective detection system. In this research, we propose the Trident of Poseidon - a novel set of triad training strategies aimed at enhancing the generalizability of deepfake voice detection models. Our solution comprises three key components: (1) Supervised Contrastive Learning, (2) Hard Negative Mining by Audio Re-synthesizing, and (3) Effective Proactive Batch Sampling. Together, these enable the model to learn more robust features. Our extensive experiments demonstrate that our approach outperforms existing methods in both in-domain and out-of-domain testing scenarios, making significant strides toward securing digital media against deepfake voice attacks. Furthermore, we conducted a deeper analysis to explore whether deepfake voices can be categorized into families. By identifying the factors that contribute to the formation of a deepfake voice family, we can better organize a deepfake voice corpus, thereby reducing the effort needed to combat the arms race challenge. Finally, to promote practical utility and community-wide adoption, we have made our solution publicly available as a web application available on deepfake.aisrc.technology, where users can utilize this tool to test for potential deepfake voices.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2222-2235
Open AccessTrident of Poseidon: A Generalized Approach for Detecting Deepfake Voices
Deepfakes, an increasingly prevalent form of information attack, pose serious threats to security and privacy. Deepfake voice attacks, in particular, have the potential to cause widespread disruption, creating an urgent need for an effective detection system. In this research, we propose the Trident of Poseidon - a novel set of triad training strategies aimed at enhancing the generalizability of deepfake voice detection models. Our solution comprises three key components: (1) Supervised Contrastive Learning, (2) Hard Negative Mining by Audio Re-synthesizing, and (3) Effective Proactive Batch Sampling. Together, these enable the model to learn more robust features. Our extensive experiments demonstrate that our approach outperforms existing methods in both in-domain and out-of-domain testing scenarios, making significant strides toward securing digital media against deepfake voice attacks. Furthermore, we conducted a deeper analysis to explore whether deepfake voices can be categorized into families. By identifying the factors that contribute to the formation of a deepfake voice family, we can better organize a deepfake voice corpus, thereby reducing the effort needed to combat the arms race challenge. Finally, to promote practical utility and community-wide adoption, we have made our solution publicly available as a web application available on deepfake.aisrc.technology, where users can utilize this tool to test for potential deepfake voices.