Mitigating dimension constraints: A novel sliding attack strategy for robust synthetic voice detection

J Liu, Z Cui, Y Zhou - Computers and Electrical Engineering, 2024 - Elsevier
With the increasing prominence of deep neural networks in synthetic voice detection, the
emergence of adversarial attacks poses a significant threat to the robustness of these …

What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection

X Hai, X Liu, Y Tan, G Liu, S Li, W Niu, R Zhou… - Proceedings of the …, 2024 - dl.acm.org
Voice is one of the most widely used media for information transmission in human society.
While high-quality synthetic voices are extensively utilized in various applications, they pose …

Ghost-in-Wave: How Speaker-Irrelative Features Interfere DeepFake Voice Detectors

X Hai, X Liu, Z Chen, Y Tan, S Li, W Niu… - … on Multimedia and …, 2024 - ieeexplore.ieee.org
Recent speech synthesis technology can generate high-quality speech indistinguishable
from human speech, thus introducing various security and privacy risks. Numerous recent …