6 papers · 1 filter
Learning to Watermark Speech Synthesis Against Model-Driven Reconstruction
Weizhi Liu, Yue Li, Hui Tian +1
Modern TTS systems increasingly generate synthetic speech at scale for diverse users. This setting calls for content-level provenance that can verify the origin of released speech…
VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
Weizhi Liu, Yue Li, Zhaoxia Yin
Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they…
CLASP: Training-Free LLM-Assisted Source Code Watermarking via Semantic-Preserving Transformations
Rui Xu, Jiawei Chen, Weizhi Liu +3
The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and intellectual property infringement. Sou…
SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation
Yue Li, Weizhi Liu, Dongdong Lin
The accelerated advancement of speech generative models has given rise to security issues, including model infringement and unauthorized abuse of content. Although existing generat…
Protecting Your Voice: Temporal-aware Robust Watermarking
Yue Li, Weizhi Liu, Dongdong Lin +2
The rapid advancement of generative models has led to the synthesis of real-fake ambiguous voices. To erase the ambiguity, embedding watermarks into the frequency-domain features o…
GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis
Weizhi Liu, Yue Li, Dongdong Lin +2
Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake…