About Me

I am a thrid-year Ph.D. student of Department of Computer Science and Engineering at Michigan State University, advised by Professor Jiliang Tang in Data Science and Engineering Lab. Before joining DSE, I was an algorithm engineer in Search Strategy Department, Baidu Inc. I got my bachelor degree from Tsinghua University.

My research interests include copyright protection in deep learning, deep generative model, and robustness of deep learning.

Email address: renjie3 at msu.edu

News

• 2024.05 One paper accepted by ECCV!
• 2024.05 Two papers accepted by ACL!
• 2024.03 I will start my internship at Sony in March.
• 2024.03 Our paper, A Robust Semantics-based Watermark for Large Language Model against Paraphrasing, is accepted by NAACL Findings.
• 2024.02 The preprint of our survey, Copyright Protection in Generative AI: A Technical Perspective, is released.
  
  

Publications

Preprint

• EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations
  Jie Ren, Yingqian Cui, Chen Chen, Vikash Sehwag, Yue Xing, Jiliang Tang, Lingjuan Lyu

• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
  Jie Ren, Kangrui Chen, Yingqian Cui, Shenglai Zeng, Hui Liu, Yue Xing, Jiliang Tang, Lingjuan Lyu

• Copyright Protection in Generative AI: A Technical Perspective
  Jie Ren, Han Xu, Pengfei He, Yingqian Cui, Shenglai Zeng, Jiankun Zhang, Hongzhi Wen, Jiayuan Ding, Hui Liu, Yi Chang, Jiliang Tang

• FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
  Yingqian Cui, Jie Ren, Yuping Lin, Han Xu, Pengfei He, Yue Xing, Wenqi Fan, Hui Liu, Jiliang Tang

Conference and Journal papers

• Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
  Jie Ren, Yaxin Li, Shenglai Zeng, Han Xu, Lingjuan Lyu, Yue Xing, Jiliang Tang
  ECCV, 2024

• Exploring Memorization in Fine-tuned Language Models
  Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Jiliang Tang, Dawei Yin
  ACL, 2024

• The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
  Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, Jiliang Tang
  ACL Findings, 2024

• A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
  Jie Ren, Han Xu, Yiding Liu, Yingqian Cui, Shuaiqiang Wang, Dawei Yin, Jiliang Tang
  Findings of NAACL, 2024

• Sharpness-Aware Data Poisoning Attack
  Pengfei He, Han Xu, Jie Ren, Yingqian Cui, Hui Liu, Charu C. Aggarwal, Jiliang Tang
  International Conference on Learning Representations (ICLR), 2024

• Neural Style Protection: Counteracting Unauthorized Neural Style Transfer
  Jie Ren*, Yaxin Li*, Han Xu, Hui Liu
  Winter Conference on Applications of Computer Vision (WACV), 2024

• DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
  Jie Ren*, Yingqian Cui*, Han Xu, Pengfei He, Hui Liu, Lichao Sun, Yue Xing, Jiliang Tang
  NeurIPS 2023 Workshop on Diffusion Models

• Probabilistic Categorical Adversarial Attack and Adversarial Training
  Penghei He, Han Xu, Jie Ren, Yuxuan Wan, Zitao Liu, Jiliang Tang.
  International Conference on Machine Learning (ICML), 2023

• Transferable Unlearnable Examples
  Jie Ren, Han Xu, Yuxuan Wan, Xingjun Ma, Lichao Sun, Jiliang Tang.
  International Conference on Learning Representations (ICLR), 2023

• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning
  Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, and Hao Wang.
  IEEE Transactions on Knowledge and Data Engineering ,2021
  (Work done as remote RA at the University of Queensland)

Tutorials

• Towards Adversarial Learning: From Evasion Attacks to Poisoning Attacks
  Wentao Wang, Han Xu, Yuxuan Wan, Jie Ren, and Jiliang Tang.
  ACM International Conference on Knowledge Discovery & Data Mining (KDD), 2022.
  
  

Invited Talk

• 11/2023. Data Protection in Deep Learning, Institute of Computing Technology, Chinese Academy of Sciences.

• 10/2023. Copyright Protection in Deep Generative Model, Qilu Youth Forum at Shandong University.

• 10/2023. Copyright Protection in Deep Generative Model. AI Time (Tsinghua University)

• 07/2023. DiffusionShield: A Watermark for Copyright Protection against GDMs, Shandong University.

• 03/2023. Transferable Unlearnable Examples, Fudan University.

Experience

• Sony AI. 03.2024 - Present
  Supervised by Dr. Lingjuan Lyu and Dr. Vikash Sehwag .
• Big Search, Baidu Inc. 12.2020 - 08.2021
  Supervised by Dr. Dawei Yin and Dr. Shuaiqiang Wang .
• Kuaishou Inc. 10.2019 - 05.2020