avatar avatar

Fengpeng Li

PostDoc Rsearch Fellow
KAUST
fengpeng.li@connect.umac.mo


About Me

I am Fengpeng Li (李风朋), currently a PostDoc Research Fellow of PRADA, King Abdullah University of Science and Technology (KAUST), advised by Prof. Di Wang. Previouly, I obtained my PhD degree in Computer Science at State Key Laboratory of Internet of Things for Smart City (SKL-IoTSC), University of Macau, advised by Prof. Jiantao Zhou. Prior to that, I earned my BS degree in Remote Sensing Science and Technology, and MS degree in Computer Science and Technology from China University of Geosciences (Wuhan), under the supervision of Prof. Lizhe Wang. I also work closely with Mr. Kemou Li, Dr. Qizhou Wang, Prof. Haiwei Wu, and Prof. Bo Han in Multimedia Forensics and Trustworthy Machine Learning, and Prof. Wei Han, and Prof. Runyu Fan in Intelligent Spatial Data Analysis and Processing.

I am currently focusing on Trustworth Machine Learning, inlcuding Robust Learning Against Malicious Threats (e.g., Adversarial Attacks, Label Noise, Adversarial Prompt Attacks and ect.), LLM Unlearning, LLM/VLM/VLA Safety Alignment and AI Agent in Spatial Data Analysis and Processing. Please feel free to contact me if you’d like to collaborate or exchange ideas on related topics :-)

News

  • [2026-02] One papers on Zero-shot AIGC Detection is accepted to CVPR 2026.
  • [2026-01] Two papers on Robust diffusion model concept erasure and LLM unlearning are accepted to ICLR 2026.
  • [2026-01] Start my PostDoc Research Fellow in PRADA Lab of KAUST.
  • [2025-12] Pass my Oral Defense Exam and Obtain my PhD Degree.
  • [2025-06] One paper on adversarial training is accepted to TIFS.
  • [2025-05] One paper on learning with noisy labels is accepted to IJCV.
  • [2024-09] One paper on adversarial training is accepted to NeurIPS 2024.
  • [2024-09] Our team wins the championship (1/706) at the Global Multimedia Deepfake Detection Challenge (Image Track) on the 2024 Inclusion Conference on the Bund.
  • [2023-12] One paper on learning with noisy labels is accepted to AAAI 2024 Oral (Top 2.2%).

Publications (* = Equal Contribution)

  1. CVPR-26
    Zero-shot Detection of AI-Generated Image via RAW-RGB Alignment
    Haiwei Wu*, Fengpeng Li*, Zhilin Tu, Yuanman Li, Xiong Li, Jiantao Zhou
    Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    CCF A

  2. ICLR-26
    AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
    Fengpeng Li, Kemou Li, Qizhou Wang, Bo Han, Jiantao Zhou
    International Conference on Learning Representations (ICLR), 2026
    PDF CCF A

  3. ICLR-26
    LLM Unlearning with LLM Beliefs
    Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Jun Liu, Bo Han, Jiantao Zhou
    International Conference on Learning Representations (ICLR), 2026
    PDF CCF A

  4. TIFS-25
    Toward Robust Deep Learning via Core Feature-aware Adversarial Training
    Fengpeng Li*, Kemou Li*, Haiwei Wu, Jinyu Tian, Jiantao Zhou
    IEEE Transactions on Information Forensics and Security (TIFS), 2025
    PDF Code CCF A

  5. IJCV-25
    RML++: Regroup Median Loss for Combating Label Noise
    Fengpeng Li, Kemou Li, Qizhou Wang, Bo Han, Jinyu Tian, Jiantao Zhou
    International Journal of Computer Vision (IJCV), 2025
    PDF Code CCF A

  6. NeurIPS-24
    DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
    Fengpeng Li, Kemou Li, Haiwei Wu, Jinyu Tian, Jiantao Zhou
    Conference on Neural Information Processing Systems (NeurIPS), 2024
    PDF Code CCF A

  7. AAAI-24 Oral
    Regroup Median Loss for Combating Label Noise
    Fengpeng Li, Kemou Li, Jinyu Tian, Jiantao Zhou
    AAAI Conference on Artificial Intelligence (AAAI), 2024
    PDF Code CCF A Oral (2.2%)

Awards & Honors

  1. Inclusion · The Global Multimedia Deepfake Detection Challenge (Image Track)
    Champion (1/706), JTGroup Team. Prize: 100,000 CNY
    Inclusion Conference on the Bund (Organized by Ant Group), 2024
    Code News

Professional Services

Journal Reviewer

Conference Reviewer

Session Chair

Teaching Experience

Teaching Assistant @UM


© 2026–2028 Fengpeng Li | Last Update: 2026.02 | Powered by Jekyll and Minimal Light theme.