Jie Ren 任杰

I am a fourth-year Ph.D. student in the Department of Computer Science and Engineering at Michigan State University, advised by Professor Jiliang Tang. Previously, I worked as an engineer in the Search Strategy Department at Baidu Inc., and I received my bachelor degree from Tsinghua University.

My research interests lie in Trustworthy and Interpretable AI, with a focus on data and model protection in Generative AI.

Email: renjie3 [at] msu.edu

Google Scholar   /   Twitter   /   Github   /   LinkedIn     

[May 2024]   I will start my internship at ByteDance in Summer 2025!

[May 2025]   One paper accepted by ACL 2025!

[Feb 2025]   One paper accepted by CVPR 2025!

[Jan 2025]   One paper accepted by AISTATS 2025!

[Jan 2025]   One paper accepted by WWW 2025 [Oral]!

EnTruth: Tracing the Unauthorized Dataset Usage in Diffusion Models
Jie Ren,  Yingqian Cui,  Chen Chen,  Vikash Sehwag,  Yue Xing,  Jiliang Tang,  Lingjuan Lyu 

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

A General Framework to Enhance Fine-tuning-based LLM Unlearning
ACL 2025 Findings 
Jie Ren,  Zhenwei Dai,  Xianfeng Tang,  Hui Liu,  Jingying Zeng,  Zhen Li,  Rahul Goutam,  Suhang Wang,  Yue Xing,  Qi He,  Hui Liu 

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
CVPR 2025 
Jie Ren*,  Kangrui Chen*,  Yingqian Cui,  Shenglai Zeng,  Hui Liu,  Yue Xing,  Jiliang Tang,  Lingjuan Lyu 

Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models
WWW 2025 [Oral] 
Jie Ren,  Kangrui Chen,  Chen Chen,  Vikash Sehwag,  Yue Xing,  Jiliang Tang,  Lingjuan Lyu 

Superiority of Multi-Head Attention in In-Context Linear Regression
AISTATS 2025 
Yingqian Cui,  Jie Ren,  Pengfei He,  Jiliang Tang,  Yue Xing 

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
SIGKDD Explorations 2024 
Yingqian Cui*,  Jie Ren*,  Han Xu,  Pengfei He,  Hui Liu,  Lichao Sun,  Yue Xing,  Jiliang Tang 

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
SIGKDD Explorations 2024 
Yingqian Cui,  Jie Ren,  Yuping Lin,  Han Xu,  Pengfei He,  Yue Xing,  Wenqi Fan,  Hui Liu,  Jiliang Tang 

Stealthy Backdoor Attack via Confidence-driven Sampling
TMLR 2024 
Pengfei He,  Han Xu,  Jie Ren,  Yingqian Cui,  Shenglai Zeng,  Yue Xing,  Jiliang Tang,  Makoto Yamada,  Mohammad Sabokrou 

On the Generalization of Training-based ChatGPT Detection Methods
EMNLP 2024 Findings 
Han Xu,  Jie Ren,  Pengfei He,  Shenglai Zeng,  Yingqian Cui,  Amy Liu,  Hui Liu,  Jiliang Tang 

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

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

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

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

Sharpness-Aware Data Poisoning Attack
ICLR 2024 [Spotlight, top %5] 
Penghei He,  Han Xu,  Jie Ren,  Yingqian Cui,  Hui Liu,  Charu C. Aggarwal,  Jiliang Tang 

Neural Style Protection: Counteracting Unauthorized Neural Style Transfer
WACV 2024 
Yaxin Li*,  Jie Ren*,  Han Xu,  Hui Liu 

Transferable Unlearnable Examples
ICLR 2023 
Jie Ren,  Han Xu,  Yuxuan Wan,  Xingjun Ma,  Lichao Sun,  Jiliang Tang 

Probabilistic Categorical Adversarial Attack and Adversarial Training
ICML 2023 
Penghei He,  Han Xu,  Jie Ren,  Yuxuan Wan,  Zitao Liu,  Jiliang Tang 

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning
TKDE 2021 
Tong Chen,  Hongzhi Yin,  Jie Ren,  Zi Huang,  Xiangliang Zhang,  Hao Wang 

Towards Adversarial Learning: From Evasion Attacks to Poisoning Attacks
KDD 2022 
Wentao Wang,  Han Xu,  Yuxuan Wan,  Jie Ren,  Jiliang Tang 

[06/2025 - 09/2025]   ByteDance, Research Intern.

[10/2024 - 05/2025]   Amazon, Applied Scientist Intern.

[03/2024 - 09/2024]   Sony AI, Research Intern.

[06/2023 - 09/2023]   Baidu, Research Intern.

[11/2020 - 08/2021]   Baidu, Full-time Search Algorithm Engineer (Level T3).

[11/2019 - 06/2020]   Kuaishou, Algorithm Engineer.

[10/2024]   Copyright Protection in Generative AI, ECAI 2024 Doctoral Consortium.

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

[10/2023]   Copyright Protection in Deep Generative Model, Shandong University.

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

[07/2023]   DiffusionShield: A Watermark for Copyright Protection against GDMs, Qilu Youth Forum at Shandong University.

[03/2023]   Transferable Unlearnable Examples, Fudan University.

PC member:   NeurIPS'24-25, AAAI'24-25, WebConf'24-25, EMNLP'24-25, CIKM'22-24, WSDM'23-25, ICLR'25, RecSys'23, CVPR'25, NAACL'25, ICML'25, ICCV'25, ACL'25

Reviewer:   TKDD, TKDE

Volunteer:   KDD'22