Dongdong Lin

Bio

Dongdong Lin is currently a lecturer at Huaqiao University, working with Hui Tian. He received his B.Sc. and M.Sc. degrees from Xiangtan University, supervised by Chengqing Li, and completed his Ph.D. at Shenzhen University, supervised by Bin Li. From 2020 to 2022, he was a visiting student at the University of Siena, Italy, working with Mauro Barni and Benedetta Tondi.

His research focuses on AI security, deep model watermarking, deepfake detection, adversarial robustness, and multimedia forensics. Recent work spans watermarking for diffusion models, speech synthesis systems, and ownership verification of generative models.

He is currently interested in trustworthy AIGC, robust model ownership protection, and security problems around modern multimodal generative systems.

He serves as a CCF Professional Member, a CSIG Member, and an IEEE Member. He also serves as a reviewer for IEEE T-IFS/DSC/ASLP, SP, CVPR, ACM MM, and ICASSP.

News

2026.08
One paper is accepted to IEEE SPL.
2026.06
One paper is accepted to ESWA.
2025.04
One paper is accepted to ICASSP.
2024.10
One paper is accepted to ACM MM.
2024.07
One paper is accepted to IEEE TDSC.

Preprints

arXiv 2026 Figure from the Diffusion-Guided Adversarial Perturbation Injection paper

Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations

Yue Li, Linying Xue, Kaiqing Lin, Hanyu Quan, Dongdong Lin, Hui Tian, Hongxia Wang, Bin Wang

arXiv preprint, 2026

PDF Paper

Adversarial ExampleDeepfake Detection

@article{li2026diffusion,
  title={Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations},
  author={Li, Yue and Xue, Linying and Lin, Kaiqing and Quan, Hanyu and Lin, Dongdong and Tian, Hui and Wang, Hongxia and Wang, Bin},
  journal={arXiv preprint arXiv:2604.01635},
  year={2026}
}
arXiv 2025 Figure from the Imperceptible Adversarial Defense paper

Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations

Yue Li, Linying Xue, Dongdong Lin, Qiushi Li, Hui Tian, Hongxia Wang

arXiv preprint, 2025

PDF Paper

Adversarial ExampleDeepfake Detection

@article{li2025towards,
  title={Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations},
  author={Li, Yue and Xue, Linying and Lin, Dongdong and Li, Qiushi and Tian, Hui and Wang, Hongxia},
  journal={arXiv preprint arXiv:2510.01699},
  year={2025}
}

Publications

SPL 2026 Figure from the Protecting Your Voice paper

Protecting Your Voice: Temporal-Aware Robust Watermarking

Yue Li, Weizhi Liu, Dongdong Lin, Hui Tian, Hongxia Wang

IEEE Signal Processing Letters, 33, 3446–3450 (2026)

Paper

Speech Watermarking

@article{li2025protecting,
  title={Protecting Your Voice: Temporal-Aware Robust Watermarking},
  author={Li, Yue and Liu, Weizhi and Lin, Dongdong and Tian, Hui and Wang, Hongxia},
  journal={IEEE Signal Processing Letters},
  year={2026},
  volume={33},
  pages={3446--3450},
  doi={10.1109/LSP.2026.3724105}
}
ESWA 2026 Figure from the latent diffusion watermarking paper

An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting

Dongdong Lin, Yue Li, Benedetta Tondi, Kaiqing Lin, Bin Li, Mauro Barni

Expert Systems with Applications, 331, 133172 (2026)

Paper

Model WatermarkingText-to-image ModelLow-Rank Adaptation

@article{LIN2026133172,
  title={An efficient watermarking method for latent diffusion models via low-rank adaptation},
  author={Lin, Dongdong and Li, Yue and Tondi, Benedetta and Li, Bin and Barni, Mauro},
  journal={Expert Systems with Applications},
  volume={331},
  pages={133172},
  year={2026},
  doi={https://doi.org/10.1016/j.eswa.2026.133172}
}
ICASSP 2025Fine Minima Optimizer

Exploiting Robust Model Watermarking Against the Model Fine-Tuning Attack via Flat Minima Aware Optimizers

Dongdong Lin, Yue Li, Bin Li, Jiwu Huang

2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Paper

Model WatermarkingWatermark RobustnessCCF-B

@inproceedings{10890107,
  author={Lin, Dongdong and Li, Yue and Li, Bin and Huang, Jiwu},
  booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title={Exploiting Robust Model Watermarking Against the Model Fine-Tuning Attack via Flat Minima Aware Optimizers},
  year={2025},
  pages={1-5},
  doi={10.1109/ICASSP49660.2025.10890107}
}
TDSC 2025 Figure from the CycleGAN watermarking paper

A CycleGAN Watermarking Method for Ownership Verification

Dongdong Lin, Benedetta Tondi, Bin Li, Mauro Barni

IEEE Transactions on Dependable and Secure Computing

Paper

GAN WatermarkingOwnership VerificationTDSC 2025CCF-A

@article{10591362,
  author={Lin, Dongdong and Tondi, Benedetta and Li, Bin and Barni, Mauro},
  journal={IEEE Transactions on Dependable and Secure Computing},
  title={A CycleGAN Watermarking Method for Ownership Verification},
  year={2025},
  volume={22},
  number={2},
  pages={1040-1054},
  doi={10.1109/TDSC.2024.3424900}
}
ACM MM 2024 Figure from the GROOT paper

GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis

Weizhi Liu, Yue Li, Dongdong Lin, Hui Tian, Haizhou Li

Proceedings of the 32nd ACM International Conference on Multimedia (ACMMM)

Paper

Audio WatermarkingACM MM 2024CCF-A

@inproceedings{10.1145/3664647.3680596,
author = {Liu, Weizhi and Li, Yue and Lin, Dongdong and Tian, Hui and Li, Haizhou},
title = {GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis},
year = {2024},
doi = {10.1145/3664647.3680596},
booktitle = {Proceedings of the 32nd ACM International Conference on Multimedia},
pages = {3294-3302},
numpages = {9}
}
PR 2023Bi-Granularity Artifacts

Watching the big artifacts: Exposing deepfake videos via bi-granularity artifacts

Han Chen, Yuezun Li, Dongdong Lin, Bin Li, Junqiang Wu

Pattern Recognition

Paper

Deepfake DetectionPR 2023CCF-B

@article{CHEN2023109179,
title = {Watching the BiG artifacts: Exposing DeepFake videos via Bi-granularity artifacts},
journal = {Pattern Recognition},
volume = {135},
pages = {109179},
year = {2023},
doi = {https://doi.org/10.1016/j.patcog.2022.109179},
author = {Han Chen and Yuezun Li and Dongdong Lin and Bin Li and Junqiang Wu}
}
IJCB 2022Temporal Transferability

Exploiting temporal information to prevent the transferability of adversarial examples against deep fake detectors

Dongdong Lin, Benedetta Tondi, Bin Li, Mauro Barni

2022 IEEE International Joint Conference on Biometrics (IJCB)

Paper

Adversarial ExampleIJCB 2022CCF-C

@inproceedings{10007959,
  author={Lin, Dongdong and Tondi, Benedetta and Li, Bin and Barni, Mauro},
  booktitle={2022 IEEE International Joint Conference on Biometrics (IJCB)},
  title={Exploiting temporal information to prevent the transferability of adversarial examples against deep fake detectors},
  year={2022},
  pages={1-8},
  doi={10.1109/IJCB54206.2022.10007959}
}
IEEE MM 2018Cryptanalysis

Cryptanalyzing an image encryption algorithm based on autoblocking and electrocardiography

Chengqing Li, Dongdong Lin, Jinhu Lu, Feng Hao

IEEE MultiMedia, 2018

Paper

CryptanalysisESI Highly Cited Paper

@article{8495009,
  author={Li, Chengqing and Lin, Dongdong and Lu, Jinhu and Hao, Feng},
  journal={IEEE MultiMedia},
  title={Cryptanalyzing an Image Encryption Algorithm Based on Autoblocking and Electrocardiography},
  year={2018},
  volume={25},
  number={4},
  pages={46-56},
  doi={10.1109/MMUL.2018.2873472}
}
IEEE MM 2017Pixel Bits Cipher

Cryptanalyzing an image-scrambling encryption algorithm of pixel bits

Chengqing Li, Dongdong Lin, Jinhu Lu

IEEE MultiMedia, 2017

Paper

CryptanalysisESI Highly Cited Paper

@article{7999153,
  author={Li, Chengqing and Lin, Dongdong and Lu, Jinhu},
  journal={IEEE MultiMedia},
  title={Cryptanalyzing an Image-Scrambling Encryption Algorithm of Pixel Bits},
  year={2017},
  volume={24},
  number={3},
  pages={64-71},
  doi={10.1109/MMUL.2017.3051512}
}