About Jun Liu
I am currently a Postdoctoral Researcher at the Echizen Lab, National Institute of Informatics (NII). I received my Ph.D. degree from the State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC) of University of Macau, under the supervision of Prof. Jiantao Zhou. My primary research interests include adversarial attack methods, privacy-preserving technologies, forensic detection, as well as security and privacy issues across various areas of artificial intelligence.
I obtained both my B.S. and M.S. degrees in Software Engineering from Beihang University. After completing my master’s degree, I worked for two years at Tencent Shenzhen, where I focused on data analysis and machine learning modeling for financial risk control.
Researchers and students who are interested in my research topics are very welcome to get in touch for discussion and collaboration.
Publications
- J. Liu, L. Y. Zhang, F. Li, I. Echizen, J. Zhou. Gradient Structure Estimation under Label-Only Oracles via Spectral Sensitivity. Arxiv 2025.
- J. Liu, J. Zhou, J. Zeng, J. Tian, I. Echizen. DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain. Arxiv 2025.
- J. Liu, J. Zhou, J. Zeng, J. Tian. Difattack: Query-efficient black-box adversarial attack via disentangled feature space. AAAI 2024.
- J. Liu, J. Zhou, J. Tian, W. Sun. Recoverable privacy-preserving image classification through noise-like adversarial examples. ACM TOMM 2024.
- J. Liu, J. Zhou, H. Wu, W. Sun, J. Tian. Generating robust adversarial examples against online social networks (osns). ACM TOMM 2024.
- K. Li, …, J. Liu, et al. LLM Unlearning with LLM Beliefs. ICLR 2026.
- H. Wu, J. Zhou, J. Tian, J. Liu, Y. Qiao. Robust image forgery detection against transmission over online social networks. IEEE TIFS 2022.
- H. Wu, J. Zhou, J. Tian, J. Liu. Robust image forgery detection over online social network shared images. CVPR Oral 2022.
- W. Sun, J. Zhou, L. Dong, J. Tian, J. Liu. Optimal pre-filtering for improving Facebook shared images. IEEE TIP 2021.
- C. Zhu, M. Wang, J. Liu, I. Echizen. EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection. Arxiv 2026.
Academic Service
Journals
- IEEE Transactions on Information Forensics and Security. (TIFS)
- IEEE Transactions on Image Processing. (TIP)
- IEEE Transactions on Dependable and Secure Computing. (TDSC)
- IEEE Transactions on Neural Networks and Learning Systems. (TNNLS)
- IEEE Transactions on Circuits and Systems for Video Technology. (TCSVT)
- IEEE Transactions on Industrial Informatics. (TII)
Conferences
- IEEE Conference on Computer Vision and Pattern Recognition. (CVPR)
- European Conference on Computer Vision. (ECCV)
- ACM International Conference on Multimedia. (ACM MM)
- The Association for the Advancement of Artificial Intelligence (AAAI)
Rewards
- 2022 H. Wu, J. Zhou, J. Liu, W. Sun. Championship in Forgery Detection Competition, 1/1561, Participant, Security AI Challenger, hosted by Alibaba and Tsinghua University.
- 2022 J. Liu, …, The Fourth Place, in Challenge of Targeted Adversarial Attacks against Face recognition, hosted by China Society of Image and Graphics.
- 2020-2025 The UM Macao PhD Scholarship, University of Macau.
- 2018 Outstanding Employee of Graduate Closed Training, Tencent.
- 2015&2018 Outstanding Graduate, Beihang University.
- 2015 Excellent Student Cadres, Beihang University.
- 2014 National Scholarship, Beihang University.
- 2014 Second Prize in the 24th “Feng Ru Cup” Competition of Academic and Technological Works, Beihang University.
- 2013-2016 First Prize Academic Award, Beihang University.
- 2011&2013 Merit Student, Beihang University.
Hobbies
- Watching movies
- Yoga
- Running and swimming
- Playing table tennis
- Playing the guzheng
- Cooking
- Strolling around
- Many more