Kecen Li

Master Student Institute of Automation Chinese Academy of Sciences

Bio

I am a third year master student at the Institute of Automation, Chinese Academy of Sciences, advised by Prof. Xinwen Hou. Before that, I obtained my bachelor's degree at Beihang University.

Contact

Email: likecen2023@ia.ac.cn

Publications

* stands for the equal contribution.

• From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
  Chen Gong*, Kecen Li*, Zinan Lin, Tianhao Wang
  USENIX Security Symposium, 2026.

• PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
  Chen Gong, Zheng Liu, Kecen Li, Tianhao Wang
  Network and Distributed System Security Symposium (NDSS), 2026.

• PrivCode: When Code Synthesis Meets Differential Privacy
  Zheng Liu, Chen Gong, Terry Yue Zhuo, Kecen Li, Weichen Yu, Matt Fredrikson, Tianhao Wang
  Network and Distributed System Security Symposium (NDSS), 2026.

• EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
  Jialin Wu*, Kecen Li*, Zhicong Huang, Xinfeng Li, Xiaofeng Wang, Cheng Hong
  IEEE Symposium on Security and Privacy (S&P), 2026.

• GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
  Kecen Li, Zhicong Huang, Xinwen Hou, Cheng Hong
  International Conference on Machine Learning (ICML), 2025.

• From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis
  Kecen Li, Chen Gong, Xiaochen Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang
  IEEE Symposium on Security and Privacy (S&P), 2025.

• DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
  Chen Gong*, Kecen Li*, Zinan Lin, Tianhao Wang
  ACM SIGSAC Conference on Computer and Communications Security (CCS), 2025.

• TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents
  Chen Gong, Kecen Li, Jin Yao, Tianhao Wang
  Network and Distributed System Security Symposium (NDSS), 2025.

• PRIVIMAGE: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining
  Kecen Li*, Chen Gong*, Zhixiang Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang
  USENIX Security Symposium, 2024.

• DAS3D: Dual-modality Anomaly Synthesis for 3D Anomaly Detection
  Kecen Li, Bingquan Dai, Jingjing Fu, Xinwen Hou
  European Conference on Computer Vision (ECCV) Workshop, 2024

• BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
  Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang
  IEEE Symposium on Security and Privacy (S&P), 2024.

• Learning-Based Pose Estimation of Non-Cooperative Spacecrafts with Uncertainty Prediction
  Kecen Li, Chenyu Hu, Haopeng Zhang
  Aerospace 2022.

Research Interests

• Data Privacy

• Machine Learning

Honors

• Outstanding Student, Beihang University, 2023

• Outstanding Student, Chinese Academy of Sciences, 2024

• Outstanding Student, Chinese Academy of Sciences, 2025