Renyang Liu

I am currently a Research Fellow at the Institute of Data Science, National University of Singapore, , under the supervision of Prof. See-Kiong Ng👨‍🏫 and collaborating closely with Prof. Tianwei Zhang👨‍🏫 from NTU, , Prof. Wenjie Feng👨‍🏫 form USTC, . Before that, I received my PhD degree 🎓 at Yunnan University, , supervised by Prof. Wei Zhou 👨‍🔬 and Prof. Shaowen Yao 👨‍🔬. 📅 From 2022 to 2023, I was a visiting student at the College of Computing and Data Science, NTU, , under the supervision of Prof. LAM, Kwok Yan 👨‍🏫. 📅 From 2023 to 2024, I am a Research Intern at the School of Cyber Security, SYSU, , supervised by Prof. Ziyu Lvy👩‍🏫.

📍 Address: Innovation 4.0 🏢, #04-06, Research Link, Singapore 117602, Singapore

💡 Research Interests

AI Security & Data Privacy 🔐
Machine Unlearning 🧹
Adversarial Attacks & Defense ⚔️
Trustworthy Generative AI 🛡️

📢 Opportunities

I welcome collaborations, research interns, and visiting students (e.g., CSC) in AI Security and related areas. If you are interested in my research topics, please send me an email for more information.

News

Jan 26, 2026	One paper on Red-teaming Unlearned Image Generation Model has been accepted by ICLR! Check it out! ✨
Jan 14, 2026	✨ Our latest paper, SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models, is now available! Check it out! ✨
Jan 14, 2026	One paper on Purifying Adversarial Perturbations for 3D Point Clouds Models has been accepted by WWW (CCF-A)! Congrats to Haoran Li!
Nov 08, 2025	Our work on misinformation detection has been accepted to AAAI (CCF-A). Many thanks to my collaborators for their outstanding contributions.✨
Jul 05, 2025	One paper on AIGC natrualness evaluation has been accepted by ACM MM (CCF-A)! Thanks to Prof. Ziyu Lyu and other awesome collaborators. Check it out! ✨
May 28, 2025	One paper on Image Generation Model Unlearning has been accepted by ACM CCS (CCF-A, Big 4)! Thanks to Prof. Wenjie Feng and other awesome collaborators. Check it out! ✨

Selected Publications

ICLR 2026

Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning

Renyang Liu, Guanlin Li, Tianwei Zhang, and See-Kiong Ng

In The Fourteenth International Conference on Learning Representations (ICLR), 2026

Bib

@inproceedings{liu2026recall,
  author = {Liu, Renyang and Li, Guanlin and Zhang, Tianwei and Ng, See-Kiong},
  title = {Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning},
  booktitle = {The Fourteenth International Conference on Learning Representations (ICLR)},
  year = {2026},
}

AAAI 2026

FACTGUARD: Event-Centric and Commonsense-Guided Fake News Detection

Jing He, Han Zhang, Yuanhui Xiao, Wei Guo, Shaowen Yao, and Renyang Liu^*

In The Fortieth AAAI Conference on Artificial Intelligence (AAAI), 2026

Bib PDF Code

@inproceedings{liu2026factguard,
  title = {FACTGUARD: Event-Centric and Commonsense-Guided Fake News Detection},
  author = {He, Jing and Zhang, Han and Xiao, Yuanhui and Guo, Wei and Yao, Shaowen and Liu, Renyang},
  booktitle = {The Fortieth AAAI Conference on Artificial Intelligence (AAAI)},
  organization = {AAAI},
  year = {2026},
}

MM 2025

D-Judge: How Far Are We? Assessing the Discrepancies Between AI-synthesized Images and Natural Images through Multimodal Guidance

Renyang Liu, Ziyu Lyu, Wei Zhou, and See-Kiong Ng

In ACM International Conference on Multimedia (MM), 2025

Bib PDF Code

@inproceedings{liu2024anid,
  title = {D-Judge: How Far Are We? Assessing the Discrepancies Between AI-synthesized Images and Natural Images through Multimodal Guidance},
  author = {Liu, Renyang and Lyu, Ziyu and Zhou, Wei and Ng, See-Kiong},
  booktitle = {ACM International Conference on Multimedia (MM)},
  organization = {ACM},
  year = {2025},
  data = {https://huggingface.co/datasets/Renyang/DANI},
}

CCS 2025

Rethinking Machine Unlearning in Image Generation Models

Renyang Liu, Wenjie Feng, Tianwei Zhang, Wei Zhou, Xueqi Cheng, and See-Kiong Ng

In ACM Conference on Computer and Communications Security (CCS), 2025

Bib PDF Code

@inproceedings{liu2025igmu,
  title = {Rethinking Machine Unlearning in Image Generation Models},
  author = {Liu, Renyang and Feng, Wenjie and Zhang, Tianwei and Zhou, Wei and Cheng, Xueqi and Ng, See-Kiong},
  booktitle = {ACM Conference on Computer and Communications Security (CCS)},
  organization = {ACM},
  year = {2025},
}

TMM 2025

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario

Renyang Liu, Kwok-Yan Lam, Wei Zhou, Sixing Wu, Jun Zhao, Dongting Hu, and Mingming Gong

IEEE Transactions on Multimedia, 2025

Bib PDF Code

@article{liu2024stba,
  title = {STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario},
  author = {Liu, Renyang and Lam, Kwok-Yan and Zhou, Wei and Wu, Sixing and Zhao, Jun and Hu, Dongting and Gong, Mingming},
  journal = {IEEE Transactions on Multimedia},
  year = {2025},
  publisher = {IEEE},
}

TIFS 2024

Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models

Renyang Liu, Wei Zhou, Tianwei Zhang, Kangjie Chen, Jun Zhao, and Kwok-Yan Lam

IEEE Transactions on Information Forensics and Security, 2024

Bib PDF Code

@article{liu2024boosting,
  title = {Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models},
  author = {Liu, Renyang and Zhou, Wei and Zhang, Tianwei and Chen, Kangjie and Zhao, Jun and Lam, Kwok-Yan},
  journal = {IEEE Transactions on Information Forensics and Security},
  year = {2024},
  publisher = {IEEE},
}