Collusion-Resilient Privacy-Preserving Database Fingerprinting
S Zhang, Y Zhu, A Zeng - IEEE Transactions on Information …, 2024 - ieeexplore.ieee.org
Database sharing may bring about privacy disclosure and illegal redistribution. A previously
proposed entry-level Differential Privacy FingerPrinting mechanism (DPFP) for relational …
proposed entry-level Differential Privacy FingerPrinting mechanism (DPFP) for relational …
HiFi-GANw: Watermarked Speech Synthesis Via Fine-Tuning of HiFi-GAN
Advancements in speech synthesis technology bring generated speech closer to natural
human voices, but they also introduce a series of potential risks, such as the dissemination …
human voices, but they also introduce a series of potential risks, such as the dissemination …
U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI
Large Generative AI (GAI) models have the unparalleled ability to generate text, images,
audio, and other forms of media that are increasingly indistinguishable from human …
audio, and other forms of media that are increasingly indistinguishable from human …
WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification
J Zhou, J Yi, Y Ren, J Tao, T Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advances in speech spoofing necessitate stronger verification mechanisms in neural
speech codecs to ensure authenticity. Current methods embed numerical watermarks before …
speech codecs to ensure authenticity. Current methods embed numerical watermarks before …
GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis
Amid the burgeoning development of generative models like diffusion models, the task of
differentiating synthesized audio from its natural counterpart grows more daunting …
differentiating synthesized audio from its natural counterpart grows more daunting …
AVSecure: An Audio-Visual Watermarking Framework for Proactive Deepfake Detection
B Guo, H Tai, G Luo, Y Zhu - 2024 IEEE 14th International …, 2024 - ieeexplore.ieee.org
The rise of Deepfake technology presents a significant challenge to the integrity of
information. Most existing Deepfake detection methods rely on visual artifacts to distinguish …
information. Most existing Deepfake detection methods rely on visual artifacts to distinguish …
Audio Forensic Analysis and Authentication Using Deep Learning
Q Li - 2024 - atrium.lib.uoguelph.ca
In the rapidly evolving digital era, the significance of audio applications across
communication, social networking, and entertainment sectors has greatly increased. This …
communication, social networking, and entertainment sectors has greatly increased. This …