activity
20242026
collaborators

6 papers

cs.CR2026

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…

cs.MM2026

TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level Traceability

Yue Li, Weizhi Liu, Kaiqing Lin +2

Diffusion-based speech generation has achieved remarkable fidelity, increasing the risk of misuse and unauthorized redistribution. However, most existing generative speech watermar…

cs.CR2026

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…

cs.CR2025

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…

cs.CR2025

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…

cs.CR2024

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…