Ziyuan He

Ziyuan He

Auto-generated profile, based on publicly available information

Ziyuan He

School of Computer Science and Technology, Xinjiang University, Urumqi, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZHZiyuan He
Ziyuan He
ZGZhiqing Guo
Zhiqing Guo
LWLiejun Wang
Liejun Wang
GYGaobo Yang
Gaobo Yang
YDYunfeng Diao
Yunfeng Diao
DMDan Ma
Dan Ma
Deepfake technology has great potential in the field of media and entertainment, but it also brings serious risks, including privacy disclosure and identity fraud. To counter these threats, proactive forensic methods have become a research hotspot by embedding invisible watermark signals to build active protection schemes. However, existing methods are vulnerable to watermark destruction under malicious distortions, which leads to insufficient robustness. Moreover, embedding strong signals may degrade image quality, making it challenging to balance robustness and imperceptibility. Although watermarked images look natural, their underlying structures are often different from the original images, which is ignored by traditional watermarking methods. To address these issues, this paper proposes a proactive watermarking framework called WaveGuard, which explores frequency domain embedding and graph-based structural consistency optimization. In this framework, the watermark is embedded into the high-frequency sub-bands by dual-tree complex wavelet transform (DT-CWT) to enhance the robustness against distortions and deepfake forgeries. By leveraging joint sub-band correlations and selected sub-band combinations, the framework enables robust source tracing and semi-robust deepfake detection. To enhance imperceptibility, we propose a Structural Consistency Graph Neural Network (SC-GNN) that constructs graph representations of the original and watermarked images to ensure structural consistency and reduce perceptual artifacts. Experimental results show that the proposed method performs exceptionally well in face swap and face replay tasks. The code has been published at https://github.com/vpsg-research/WaveGuard.

5 June 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZHZiyuan He
Ziyuan He
ZGZhiqing Guo
Zhiqing Guo
LWLiejun Wang
Liejun Wang
XTXiaoming Tao
Xiaoming Tao
XLXin Liao
Xin Liao
Proactive forensic methods based on watermarking have attracted increasing attention as an effective paradigm for deepfake detection and source tracing. However, the existing methods still have shortcomings in encryption security, robustness and detection performance when dealing with complex forgery. In this paper, we propose a region-aware watermarking based proactive deepfake detection framework named Segfacemark. Building on global watermark embedding, this method explicitly models the sensitivity of various semantic facial regions to tampering. By employing region-wise partitioning and redundant embedding, the framework strengthens the protection of key facial areas, thereby comprehensively enhancing watermark robustness. In addition, the proposed framework employs a dynamic encryption mechanism that derives personalized keys from identity features to encrypt structural features, thereby realizing a “one-identity–one-key” watermark generation strategy and significantly enhancing system security and robustness against forgery. In the detection stage, the dual verification mechanism of identity decryption consistency and global region-aware watermark consistency not only improves detection accuracy but also enables forgery type identification, and further enhances the interpretability of deepfake detection results through region-aware watermarks. Experimental results show that the proposed method achieves high accuracy and robustness in deepfake detection, while preserving visual fidelity. The code will be released at: https://github.com/vpsg-research/Segfacemark.