avatar

Mengnan Zhao

Tenure-track Assoc. Prof
Computer science，AHU
gaoshanxingzhi@163.com

Publications

Selected first-author works are listed first, followed by manuscripts under review and representative collaborative papers.

Selected Publications

  1. CVPR
    Mitigating Error Amplification in Fast Adversarial Training
    Mengnan Zhao, Lihe Zhang, BoWang, Tianhang Zheng, Hong Zhong, Geyong Min
    Computer Vision and Pattern Recognition, 2026.
    ConferenceCCF A
    Website PDF GitHub Package BibTeX arXiv.org
  2. ECCV
    Catastrophic Overfitting: A Potential Blessing in Disguise
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
    European Conference on Computer Vision, 2024.
    ConferenceCCF BCAA A
    Website PDF GitHub Package BibTeX arXiv.org
  3. ICCV
    Fast adversarial training with smooth convergence
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
    International Conference on Computer Vision, 2023.
    ConferenceCCF A
    Website PDF GitHub Package BibTeX arXiv.org
  4. SCIS
    ShallowUnlearn: Rethinking concept unlearning through disentangled component-level erasure in text-guided diffusion models
    Mengnan Zhao, Tianhang Zheng, Bo Wang, Lihe Zhang, Baocai Yin
    中国科学-信息科学, 2026.
    JournalCCF A
    Website PDF GitHub Package BibTeX arXiv.org
  5. SCIS
    Movable-type eraser: separable, recoverable, and sustainable multi-concept eraser in diffusion models
    Mengnan Zhao, Lihe Zhang, Baocai Yin
    中国科学-信息科学, 2026.
    JournalCCF A
    Website PDF GitHub Package BibTeX arXiv.org
  6. TIFS
    Adversarial Attacks on Scene Graph Generation
    Mengnan Zhao, Lihe Zhang, Wei Wang, Yuqiu Kong, Baocai Yin
    IEEE Transactions on Information Forensics and Security, 2024.
    JournalCCF A
    Website PDF GitHub Package BibTeX arXiv.org
  7. TIFS
    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.
    JournalCCF A
    Website PDF GitHub Package BibTeX arXiv.org
  8. PR
    Class Correlation Correction for Unbised Scene Graph Generation
    Mengnan Zhao, Yuqiu Kong, Lihe Zhang, Baocai Yin
    Pattern Recognition, 2023.
    JournalSCI ICCF B
    Website PDF GitHub Package BibTeX arXiv.org
  9. TCSVT
    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.
    JournalSCI ICCF B
    Website PDF GitHub Package BibTeX arXiv.org
  10. TCSVT
    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.
    JournalSCI ICCF B
    Website PDF GitHub Package BibTeX arXiv.org
  11. ESWA
    EipFormer: Enhancing 3D Instance Segmentation by Emphasizing Instance Positions
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
    Expert Systems With Applications, 2024.
    JournalSCI I
    Website PDF GitHub Package BibTeX arXiv.org
  12. APID
    Temporal Knowledge Graph Reasoning Triggered by Memories
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
    Applied Intelligence, 2023.
    JournalSCI IICCF C
    Website PDF GitHub Package BibTeX arXiv.org
  13. Neuro
    Protecting by Attacking: A Personal Information Protecting Method with Cross-Modal Adversarial Examples
    Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
    Neurocomputing, 2023.
    JournalSCI IICCF C
    Website PDF GitHub Package BibTeX arXiv.org
  14. 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.
    Conference
    Website PDF GitHub Package BibTeX arXiv.org
  15. 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**, before warning 2019.
    JournalSCI
    Website PDF GitHub Package BibTeX arXiv.org

In Peer Review / Preprints

  1. arXiv
    Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training
    Mengnan Zhao, Geyong Min, Lihe Zhang, Tianhang Zheng, Jie Cui
    arXiv preprint, 2026.
    In Peer ReviewPreprintRobust Learning
  2. arXiv
    Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
    Mengnan Zhao, Lihe Zhang, Tianhang Zheng, Bo Wang, Baocai Yin
    arXiv preprint, 2026.
    In Peer ReviewPreprintAdversarial Training
  3. arXiv
    AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors
    Mengnan Zhao, Lihe Zhang, Xingyi Yang, Tianhang Zheng, Baocai Yin
    arXiv preprint, 2025.
    In Peer ReviewPreprintDiffusion Unlearning
  4. arXiv
    Adversarial Training: A Survey
    Mengnan Zhao, Lihe Zhang, Jingwen Ye, Huchuan Lu, Baocai Yin, Xinchao Wang
    arXiv preprint, 2024.
    In Peer ReviewPreprintSurvey

Collaborative Papers

  1. TCSVT
    BadPromptFL: Parameters-Free Backdoor Attack on Vision-Language Federated Learning
    Maozhen Zhang, Mengnan Zhao, Wei Wang, Tianhang Zheng, Bo Wang
    IEEE Transactions on Circuits and Systems for Video Technology, 2026.
    CollaborativeJournalSCI ICCF B
  2. IoTJ
    Stealthy Backdoor Carriers: The Threat of Visual Prompts to CLIP
    Maozhen Zhang, Mengnan Zhao, Wei Wang, Bo Wang
    IEEE Internet of Things Journal, 2026.
    CollaborativeJournalSCI I
  3. KBS
    DualVeil: Persistent and Invisible Backdoor Attacks in Federated Learning via Dual Optimization
    Maozhen Zhang, Mengnan Zhao, Wei Wang, Bo Wang
    Knowledge-Based Systems, 2026.
    CollaborativeJournalSCI ICCF C
  4. arXiv
    ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions
    Xinzhe Huang, Biwu Yao, Kedong Xiu, Mengnan Zhao, Di Wang, Puning Zhao, Tianhang Zheng
    arXiv preprint, 2026.
    CollaborativePreprintLLM Safety
  5. arXiv
    AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
    Ruoyu Wang, Heng Zhao, Renjie Wu, Mengnan Zhao, Zhixuan Chu, Wanyu Lin, Tianhang Zheng
    arXiv preprint, 2026.
    CollaborativePreprintAgent Security
  6. arXiv
    Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
    Bo Wang, Jia Ni, Mengnan Zhao, Zhan Qin, Kui Ren
    arXiv preprint, 2026.
    CollaborativePreprintData Protection
  7. EMNLP
    Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
    Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam
    Proceedings of EMNLP: Industry Track, 2025.
    CollaborativeConferenceCCF B
  8. TMM
    CollabLearn: Propelling Weakly-Supervised Referring Image Segmentation Through Collaboration Between Semantics and Details
    Chao Jiang, Yuqiu Kong, Mengnan Zhao, Lihe Zhang, Baocai Yin
    IEEE Transactions on Multimedia, 2025.
    CollaborativeJournalSCI ICCF B