Mengnan Zhao

About Me

Mengnan, Zhao received his Ms. degree under the supervision of Prof. Bo Wang in 2021, and his Ph.D degree under the supervision of Prof. Baocai Yin, Prof. Lihe Zhang and Dr. Yuqiu Kong in 2025. He is also a visiting Ph.D. of Learning and Vision (LV) Lab at the National University of Singapore under the supervision of Prof. Xinchao Wang.

👋 Feel free to contact Mengnan by Email or WeChat(15822843520).

🙏 2024Lucky -> ME <- 2024Lucky 🙏 Negative examples: AAAI2024 Rej-(wa,wa,wa,wr); CVPR2024 Rej-(wa,wa,wr).

Work

2025.09, Resigned from the Assist. Prof. position at South China University of Technology. Welcome to consult!
2025.03, Back from a CSC visiting program at NUS. Open to inquiries！
2021.03, Internships in Institute of Automation, Chinese Academy of Sciences. w. Prof. Wei Wang.

Honors

2024 China Association for Science and Technology Youth Talent PhD Program (Computer Society)
2024 Outstanding Graduate of Liaoning Province
2024 National PhD Scholarship (China)
2024 Outstanding Graduate of Dalian University of Technology
2024 Dalian University of Technology PhD Individual Award (Academic Excellence)
2024 Excellent Postgraduate Student of Dalian University of Technology
2023 Excellent Postgraduate Student of Dalian University of Technology

Research Interests

Security and Privacy: watermark and machine unlearn,
Adversarial: adversarial attack and adversarial trianing,
Fairness: prediction debiasing
Machine Learning: 3D scene understanding
Knowledge Graph: Temporal knowledge graph reasoning

News (1st author) 🎉

TOP [C]/[J]: ICCV, ECCV, TIFS, TCSVT, PR

[2025-07] One paper on 3D Instance Segmentation is accepted by ESWA.
[2025-06] Obtain my Ph.D degree from DUT.
[2024-07] One paper on Fast Adversarial Training is accepted by ECCV.
[2024-01] One paper on Scene Graph Generation Attack is accepted by IEEE TIFS.
[2023-12] One paper on Unbised Scene Graph Generation is accepted by PR.
[2023-10] One paper on Knowledge Graph Reasoning is accepted by Applied Intelligence.
[2023-10] One paper on Fast Adversarial Training is accepted by ICCV.
[2023-09] One paper on Image Captioning Attack is accepted by Neurocomputing.
[2022-07] One paper on Adversarial Attack is accepted by ICAIS.
[2022-06] One paper on Adversarial Attack is accepted by IEEE TIFS.
[2021-06] Obtain my Ms. degree from DUT.
[2020-12] One paper on Adversarial Attack is accepted by IEEE TCSVT.
[2020-08] One paper on Adversarial Attack is accepted by IEEE TCSVT.
[2019-12] One paper on SCI is accepted by IEEE Access (Direct Accept. Before Warning).

Publications and Projects

arXiv

Catastrophic Overfitting: A Potential Blessing in Disguise

Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin

European Conference on Computer Vision, 2024.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Adversarial Attacks on Scene Graph Generation

Mengnan Zhao, Lihe Zhang, Wei Wang, Yuqiu Kong, Baocai Yin

IEEE Transactions on Information Forensics and Security, 2024.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Class Correlation Correction for Unbised Scene Graph Generation

Mengnan Zhao, Yuqiu Kong, Lihe Zhang, Baocai Yin

Pattern Recognition, 2023.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Temporal Knowledge Graph Reasoning Triggered by Memories

Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin

Applied Intelligence, 2023.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Fast adversarial training with smooth convergence

Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin

International Conference on Computer Vision, 2023.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Protecting by Attacking: A Personal Information Protecting Method with Cross-Modal Adversarial Examples

Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin

Neurocomputing, 2023.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Further Understanding Towards Sparsity Adversarial Attacks

Mengnan Zhao, Xiaorui Dai, Bo Wang, Fei Yu, Fei Wei

International Conference on Artificial Intelligence and Security, 2022.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Guided erasable adversarial attack (GEAA) toward shared data protection

Mengnan Zhao, Bo Wang, Wei Wang, Tianhang Zheng, Kui Ren

IEEE Transactions on Information Forensics and Security, 2022.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Adversarial analysis for source camera identification

Bo Wang (Ms. Tutor), Mengnan Zhao, Wei Wang, Xiaorui Dai, Yi Li, Yanqing Guo

IEEE Transactions on Circuits and Systems for Video Technology, 2021.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Are You Confident That You Have Successfully Generated Adversarial Examples

Bo Wang (Ms. Tutor), Mengnan Zhao, Wei Wang, Fei Wei, Zhan Qin, Kui Ren

IEEE Transactions on Circuits and Systems for Video Technology, 2020.

Website PDF GitHub Package BibTeX arXiv.org
arXiv

Source Camera Identification Based on Coupling Coding and Adaptive Filter

Mengnan Zhao, Bo Wang, Fei Wei, Meineng Zhu, Xue Sui

IEEE Access, direct accept, 2019.

Website PDF GitHub Package BibTeX arXiv.org

Patents.

A Reasonable Adv Analysis Method for Source Camera Recognition [link].
CN112381149A
Mengnan Zhao, Bo Wang
An Source Identification Method Based on Adaptive Filtering and Coupled Encoding [link].
ZL201910871685.X; CN110659679
Mengnan Zhao, Bo Wang
A Point Attack Method Based on Weighted Spectrum Generation of Adv Samples [link].
ZL201911050075.X; CN110866287B
Mengnan Zhao, Bo Wang
A Defense Method Based on Deceptive Attackers to Adv Samples [link].
ZL201911050099.5; CN110852363B
Bo Wang (Ms. Tutor), Mengnan Zhao
A Targeted Adv Poisoning Attack Method for Shared Data Protection [link]
CN113821770A
Mengnan Zhao, Bo Wang

Professional Service.

Reviewer for:

[C]. CVPR, ICCV, ECCV, NIPS, ACMM…
[J]. TIFS, TCSVT, TMM, TNNLS, TNSE, ESWA, EAAI…