个人简介

娄坚，副教授，博士生导师。曾于美国埃默里大学(Emory University)从事博士后研究工作。主要研究方向包括可信人工智能、可信大模型、人工智能隐私保护、数据隐私保护、数据质量评估等。近年来在人工智能、安全与隐私保护、数据库等领域发表论文70余篇，其中NeurIPS、ICML、ACM CCS、IEEE S&P、USENIX Sec、ICCV、CVPR、SIGMOD、VLDB、WWW、IEEE TDSC等CCF-A或中科院一区论文40余篇，获得安全与隐私保护国际顶级会议ACM CCS 2024杰出论文奖(Distinguished Paper Award)，澳洲密码年会ACISP 2025最佳论文奖(Best Paper Award)，国际会议IEEE/WIC/ACM WI-IAT 2020最佳理论论文奖(Best in Theoretical Paper Award)等，研究成果曾获国际知名科技媒体New Scientist报道。担任人工智能顶会ICML、ICLR领域主席、AAAI高级程序委员，安全与隐私保护顶会ACM CCS程序委员，数据库顶会VLDB程序委员。

常年招收大模型安全与隐私保护方向博士后，常年招收大二、大三有志于科研的本科生，欢迎感兴趣的同学联系！

课题组快讯

2025/09：一篇论文获信息安全顶刊TDSC录用

2025/08：一篇论文获信息安全顶会CCS 2025录用

2025/08：获邀担任ICLR 2026领域主席、CCS 2026程序委员

2025/08：指导本科生获全国高校电气电子工程创新大赛一等奖与二等奖

2025/08：两篇论文分别获EMNLP Findings 2025、CIKM 2025录用

2025/07：获澳洲密码年会ACISP最佳论文奖

2025/07：获邀担任AAAI 2026高级程序委员

2025/06：一篇论文获信息安全顶会USENIX Security 2025录用

2025/05：三篇论文获人工智能顶会ICML 2025录用

2025/05：两篇论文分别获人工智能顶会IJCAI 2025、ACL Findings 2025录用

学术服务

  • 领域主席(Area Chair): 人工智能顶会ICLR 2026； ICML 2024-2025
  • 高级程序委员(Senior PC Member): 人工智能顶会AAAI 2025-2026
  • 程序委员(PC Member): 信息安全顶会ACM CCS 2024-2026、2022；IEEE EuroS&P 2025；数据库顶会VLDB 2023-2024
  • 审稿人：NeurIPS、ICLR、KDD、AAAI、IJCAI、TDSC、TKDE等顶会顶刊

研究与招生

招生方向包括但不限于可信大模型、大模型安全与隐私保护、数据质量评估、数据隐私保护等。课题组为科研表现优异的同学提供多种形式的海内外高校学术交流访问和深造机会，为优秀硕士生提供硕转博衔接培养机会。

  • 欢迎有意来37000vip威尼斯做博士后的同学与我们联系，目前我们团队依托学院可信大模型研究中心招收多名博士后！
  • 欢迎对科研感兴趣或想体验科研的本科同学加入我们，参与科研实习、大创、学科竞赛、答疑解惑等形式都可以！

联系方式为邮箱louj5@mail.sysu.edu.cn或软工学院323线下交流。

代表性论文

（全部列表详见个人主页https://sites.google.com/view/jianlou，其中*代表指导的学生）

2025

  1. [ACISP] Xiaoyu Zhang, Yong Lin, Meixia Miao, Jian Lou, Jin Li, Xiaofeng Chen, “Zeroth-Order Federated Private Tuning for Pretrained Large Language Models", ACISP'25 (Best Paper Award).
  2. [ACM CCS, CCF-A] with Chenyang Zhang*, Xiaoyu Zhang, Kai Wu, “PreferCare: Preference Dataset Copyright Protection in LLM Alignment by Watermark Injection and Verification", ACM CCS'25.
  3. [USENIX Sec, CCF-A] with Jiawen Zhang*, Kejia Chen*, Lipeng He, Dan Li, Zunlei Feng, Mingli Song, Jian Liu, Kui Ren, Xiaohu Yang, “Activation Approximations Can Incur Safety Vulnerabilities in Aligned LLMs: Comprehensive Analysis and Defense", USENIX Sec'25.[arXiv]
  4. [ICML, CCF-A] with Chenyang Zhang*, Xiaoyu Zhang, Kai Wu, Zilong Wang, Xiaofeng Chen, “PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models", ICML'25.[Link]
  5. [ICML, CCF-A] with Kejia Chen*, Jiawen Zhang*, Jiacong Hu, Yu Wang, Zunlei Feng, Mingli Song, “Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models", ICML'25.[Link]
  6. [ICML, CCF-A] Yuecheng Li, Lele Fu, Tong Wang, Jian Lou, Bin Chen, Lei Yang, Jian Shen, Zibin Zheng, Chuan Chen, “Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off",ICML'25.[arXiv]
  7. [IJCAI, CCF-A] Hong kyu Lee, Qiuchen Zhang, Carl Yang, Jian Lou, Li Xiong,“Contrastive Unlearning: A Contrastive Approach to Machine Unlearning", IJCAI'25.[arXiv]
  8. [CIKM] Zhuomin Chen*, Dan Li, Jiahui Zhou*, Shunyu Wu*, Haozhen Ye*, Jian Lou, See-Kiong Ng, “Activation Approximations Can Incur Safety Vulnerabilities in Aligned LLMs: Comprehensive Analysis and Defense", CIKM'25.
  9. [ACL, CCF-A] Yukai Zhou, Jian Lou, Zhijie Huang, Zhan Qin, Sibei Yang, Wenjie Wang, “Don't Say No: Jailbreaking LLM by Suppressing Refusal", ACL Findings'25.[arXiv]
  10. [EMNLP, CCF-A] Fenghua Weng, Jian Lou, Jun Feng, Minlie Huang, Wenjie Wang, “Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training", EMNLP Findings'25.[arXiv]
  11. [AMIA] Yifei Ren, Linghui Zeng,Jian Lou, Li Xiong, Joyce Ho, Xiaoqian Jiang, Sivasubramanium Bhavani, “Unraveling Complex Temporal Patterns in EHRs via Robust Irregular Tensor Factorization", AMIA Informatics Summit'25.
  12. [TDSC, CCF-A] Qiao Xue, Qingqing Ye, Haibo Hu, Jian Lou, Jin Li, Chengfang Fang, Jie Shi, “LabelDP Leaks Privacy – A Tightened Correlation-aware Privacy Model for Labeled Training Data", IEEE Transactions on Dependable and Secure Computing, 2025.
  13. [TMM] Xiaoyu Zhang, Yulin Jin, Haoyu Tong, Jian Lou, Kai Wu, Xiaofeng Chen, “Purifier+ : Plug-and-play Backdoor Mitigation for Pre-trained Models via Activation Alignment", IEEE Transactions on Multimedia, 2025.
  14. Congcong Fu*, Hui Li, Jian Lou, Jiangtao Cui, “Towards Answering Analytical Query over Hierarchical Histogram under Untrusted Servers", Distributed Parallel Databases, 2025.

2024

  1. [ACM CCS, CCF-A] Junxu Liu, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng, “Cross-silo Federated Learning with Record-level Personalized Differential Privacy", ACM CCS'24 (Distinguished Paper Award).
  2. [ACM CCS, CCF-A] with Yuke Hu*, Jiaqi Liu*, Wangze Ni, Feng Lin, Zhan Qin, Kui Ren, “ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach", ACM CCS'24.
  3. [S&P, CCF-A] with Hongwei Yao*, Zhan Qin, Kui Ren, “PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", S&P/Oakland'24.
  4. [TDSC, CCF-A] with Xiaoyu Zhang, Chenyang Zhang*,Kai Wu, Zilong Wang, Xiaofeng Chen, “DuplexGuard: Safeguarding Deletion Right in Machine Unlearning via Duplex Watermarking", IEEE Transactions on Dependable and Secure Computing, 2024.
  5. [AAAI, CCF-A] with Wenjie Wang, Pengfei Tang, Yuanming Shao, Lance Waller, Yi-an Ko, Li Xiong, “IGAMT: Privacy Preserved Electronic Health Record Synthetic Approach with Heterogeneity and Irregularity", AAAI'24.
  6. [ECAI] with Jiawen Zhang*, Kejia Chen*, Zunlei Feng, Mingli Song, “SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models", ECAI'24.
  7. [NeurIPS, CCF-A] Kai Wu, Yujian Li,Jian Lou, Xiaoyu Zhang, Handing Wang, Jing Liu, “Rapid Plug-in Defenders", NeurIPS'24.
  8. [SIGMOD, CCF-A] Congcong Fu*, Hui Li, Jian Lou, Huizhen Li, Jiangtao Cui, “DP-starJ: A Differentially Private Scheme towards Analytical Star-Join Queries", SIGMOD'24.
  9. [SIGMOD, CCF-A] Xiaochen Li, Weiran Liu, Jian Lou, Yuan Hong, Lei Zhang, Zhan Qin, Kui Ren, “Local Differentially Private Heavy Hitter Detection in Data Streams with Bounded Memory", SIGMOD'24.
  10. [CVPR, CCF-A] Wen Yin, Jian Lou, Pan Zhou, Yulai Xie, Dan Feng, Yuhua Sun, Tailai Zhang, Lichao Sun, “Temperature-based Backdoor Attacks on Thermal Infrared Object Detection", CVPR'24.
  11. [WWW, CCF-A] Qiuchen Zhang, Hong kyu Lee, Jing Ma, Jian Lou, Carl Yang, Li Xiong,“DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy", WWW'24.
  12. [AAAI, CCF-A] Lanlan Chen,Kai Wu, Jian Lou, Jing Liu, “Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics", AAAI'24.
  13. [ACM MMv] Haoyu Tong*, Xiaoyu Zhang, Yulin Jin*, Jian Lou, Kai Wu, Xiaofeng Chen, “Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions", ACM MM'24.
  14. [DBSec] Fereshteh Razmi, Jian Lou, Li Xiong, “Does Differential Privacy Prevent Backdoor Attacks in Practice?", DBSec'24.
  15. [ICASSP] Hongwei Yao*, Jian Lou,Zhan Qin, “PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models", ICASSP'24.
  16. [TDSC, CCF-A] Yuchen Yang*, Bo Yuan*,Jian Lou, Zhan Qin, “SCRR: Stable Malware Detection under Unknown Deployment Environment Shift by Decoupled Spurious Correlations Filtering", IEEE Transactions on Dependable and Secure Computing, 2024.
  17. [TDSC, CCF-A] Yuke Hu*, Yang Wang, Jian Lou, Wei Liang, Ruofan Wu, Weiqiang Wang, Xiaochen Li, Jinfei Liu, Zhan Qin, “Privacy Risks of Federated Knowledge Graph Embedding: New Membership Inference Attacks and Personalized Differential Privacy Defense", IEEE Transactions on Dependable and Secure Computing, 2024.
  18. Chenyang Chen, Xiaoyu Zhang, Hongyi Qiu, Jian Lou, Zhengyang Liu, Xiaofeng Chen, “MaskArmor: Confidence Masking-based Defense Mechanism for GNN against MIA", Information Science, 2024.

2023

  1. [ACM CCS, CCF-A] Yiling He*, Jian Lou, Zhan Qin, Kui Ren, “FINER: Enhancing State-of-the-art Classifiers with Feature  Attribution to Facilitate Risk Analysis", ACM CCS'23.
  2. [NeurIPS, CCF-A] with Jiaqi Liu*, Zhan Qin, Kui Ren, “Certified Minimax Unlearning with Generalization Rates and Deletion Capacity", NeurIPS'23.
  3. [ICCV, CCF-A] with Junxu Liu*, Mingsheng Xue*, Xiaoyu Zhang, Li Xiong, Zhan Qin, “MUter: Machine Unlearning on Adversarial Training Models", ICCV'23.
  4. [ACM MM, CCF-A] with Yulin Jin*, Xiaoyu Zhang, Xiaofeng Chen, “ACQ: Few-shot Backdoor Defense via Activation Clipping and Quantizing", ACM MM'23.
  5. [CIKM] with Shuijing Zhang*, Li Xiong, Xiaoyu Zhang, Jing Liu, “Closed-form Machine Unlearning for Matrix Factorization", CIKM'23.
  6. [NeurIPS, CCF-A] Jinfei Liu, Pengyun Zhu, Long Wen, Feng Xue, Jian Lou, et al., “CAPP-130 : A Dataset of Chinese Application Privacy Policy Summarization and Interpretations", NeurIPS'23 Datasets and Benchmarks Track.
  7. [VLDB, CCF-A] Haocheng Xia, Jinfei Liu, Jian Lou, Zhan Qin, Kui Ren, Yang Cao, Li Xiong, “Equitable Data Valuation Meets the Right to be Forgotten in Model Markets", VLDB'23.
  8. [ICCV, CCF-A] Yulin Jin*, Xiaoyu Zhang, Jian Lou, Xu Ma, Xiaofeng Chen, Zilong Wang, “Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective", ICCV'23.
  9. [CIKM] Junxu Liu, Jian Lou, Li Xiong, Xiaofeng Meng, “Personalized Differentially Private Federated Learning without Exposing Privacy Budgets", CIKM'23.
  10. [ECML-PKDD] Fereshteh Razmi, Jian Lou,Li Xiong, Yuan Hong, “Interpretation Attacks on Interpretable Models with Electronic Health Records", ECML-PKDD'23.
  11. [ML4H] Yifei Ren*, Jian Lou, Li Xiong, Joyce Ho, Xiaoqian Jiang, Sivasubramanium Bhavani, “MULTIPAR: Supervised Irregular Tensor Factorization with Multi-task Learning", ML4H'23.
  12. [TDSC, CCF-A] Hongwei Yao*, Zheng Li, Kunzhe Huang, Jian Lou, et al., “RemovalNet: DNN Fingerprint Removal Attacks", IEEE Transactions on Dependable and Secure Computing, 2023.

2022

  1. [ACM MM, CCF-A] with Xiaoyu Zhang, Yulin Jin*, Tao Wang, Xiaofeng Chen, “Purifier: Plug-and-play Backdoor Mitigation for Pre-trained Models Via Anomaly Activation Suppression", ACM MM'22.
  2. [ACM MM, CCF-A] Yuhua Sun, Tailai Zhang, Xingjun Ma, Pan Zhou, Jian Lou, Zichuan Xu, Xing Di, Yu Cheng, Lichao Sun, “Backdoor Attacks on Crowd Counting", ACM MM'22.
  3. [VLDB, CCF-A] Junxu Liu*, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng, “Projected Federated Averaging with Heterogeneous Differential Privacy", VLDB'22.
  4. [ICDM] Kaixin Yuan*, Jing Liu, Jian Lou, “Higher-Order Masked Graph Neural Networks for Traffic Flow Prediction", ICDM'22.
  5. [CIKM] Farnaz Tahmasebian*, Jian Lou, Li Xiong, “RobustFed: A Truth Inference Approach for Robust Federated Learning", CIKM'22.
  6. [CIKM] Congcong Fu*, Hui Li, Jian Lou, Jiangtao Cui, “DP-HORUS: Differentially Private Hierarchical Count Histograms under Untrusted Server", CIKM'22.
  7. [TDSC, CCF-A] Pengfei Tang*, Wenjie Wang*, Jian Lou, Li Xiong, “Generating Adversarial Examples with Distance Constrained Adversarial Imitation Networks", IEEE Transactions on Dependable and Secure Computing, 2022.

2021

  1. [ICCV, CCF-A] with Haowen Lin*, Li Xiong, Cyrus Shahabi, “Integer-arithmetic-only Certified Robustness for Quantized Neural Networks", ICCV'21.
  2. [WWW, CCF-A] with Jing Ma*, Qiuchen Zhang*, Li Xiong, Joyce Ho, “Communication Efficient Federated Generalized Tensor Factorization for Collaborative Health Data Analytics", WWW'21.
  3. [IJCAI, CCF-A] with Qiuchen Zhang*, Jing Ma*, Li Xiong, “Private Stochastic Non-convex Optimization with Improved Utility Rates", IJCAI'21. 
  4. [NAACL] with Wenjie Wang*, Pengfei Tang*, Li Xiong, “Certified Robustness to Word Substitution Attack with Differential Privacy",  NAACL'21.
  5. [TNNLS] with Yiu-ming Cheung, “An Uplink Communication Efficient Approach to Feature-wise Distributed Sparse Optimization with Differential Privacy”, IEEE Transactions on Neural Networks and Learning Systems, 2021.
  6. [VLDB, CCF-A] Jinfei Liu, Jian Lou, Junxu Liu, Li Xiong, Jian Pei, Jimeng Sun, “Dealer: An End-to-End Model Marketplace with Differential Privacy", VLDB'21.
  7. [VLDB, CCF-A] Jinfei Liu, Qiongqiong Lin, Jiayao Zhang, et al., “Demonstration of Dealer: An End-to-End Model Marketplace with Differential Privacy",  VLDB'21 Demo Track.
  8. [ICDM] Jing Ma*, Qiuchen Zhang*, Jian Lou, Li Xiong, Joyce Ho, Sivasubramanium Bhavani, “Communication Efficient Tensor Factorization for Decentralized Healthcare Networks", ICDM'21.
  9. [CIKM] Jing Ma*, Qiuchen Zhang*, Jian Lou, Li Xiong, Joyce Ho, “Temporal Network Embedding via Tensor Factorization", CIKM'21.
  10. [WISE] Yiu-ming Cheung, Jian Lou, Feng Yu, “Vertical Federated Principal Component Analysis on Feature-wise Distributed Data", WISE'21.
  11. [TCYB] Qiquan Shi, Yiu-ming Cheung, Jian Lou, “Robust Tensor SVD and Recovery with Rank Estimation", IEEE Transactions on Cybernetics, 2021. 

2020

  1. [WI-IAT] with Yiu-ming Cheung, “Projection-free Online Empirical Risk Minimization with Privacy-preserving and Privacy Expiration", WI-IAT'20 (Best in Theoretical Paper Award).
  2. [CIKM] with Yifei Ren*, Li Xiong, Joyce Ho, “Robust Irregular Tensor Factorization and Completion for Temporal Health Data Analysis",CIKM'20.
  3. [TIP, CCF-A] with Yiu-ming Cheung, “Robust Low-rank Tensor Minimization via a New Tensor Spectral k-Support Norm”, IEEE Transactions on Image Processing, 2020.
  4. [Bigdata] Qiuchen Zhang*, Jing Ma*, Yonghui Xiao, Jian Lou, Li Xiong, “Broadening Differential Privacy for Deep Learning Against Model Inversion Attacks", Bigdata'20.
  5. [Bigdata] Qiuchen Zhang*, Jing Ma*, Jian Lou, Li Xiong, Xiaoqian Jiang, “Towards Training Robust Private Aggregation of Teacher Ensembles Under Noisy Labels", Bigdata'20.
  6. [TIFS, CCF-A] Meng Pang, Yiu-ming Cheung, Binghui Wang, Jian Lou, “Synergistic Generic Learning for Face Recognition From a Contaminated Single Sample per Person", IEEE Transactions on Information Forensics and Security, 2020.

2019 and before

  1. [CIKM] Jing Ma*, Qiuchen Zhang*, Jian Lou, Joyce Ho, Li Xiong, Xiaoqian Jiang, "Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis", CIKM'19.
  2. [MICCAI] with Wenwen Li, Shuo Zhou, Haiping Lu, “Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI", MLMI@MICCAI'19.
  3. [AAAI, CCF-A] with Yiu-ming Cheung, "Uplink Communication Efficient Differentially Private Sparse Optimization With Feature-Wise Distributed Data", AAAI'18.
  4. [TCSVT] Meng Pang, Yiu-ming Cheung, Risheng Liu, Jian Lou, and Chuang Lin, “Toward efficient image representation: Sparse concept discriminant matrix factorization", IEEE Transactions on Circuits and Systems for Video Technology, 2018.
  5. [ML] with Yiu-ming Cheung, “Proximal Average Approximated Incremental Gradient Descent for Composite Penalty Regularized Empirical Risk Minimization”, Machine Learning, 2017.
  6. [CIKM] with Yiu-ming Cheung, “Scalable Spectral k-Support Norm Regularization for Robust Low Rank Subspace Learning", CIKM'16.
  7. [IJCAI, CCF-A] with Yiu-ming Cheung, “Efficient Generalized Conditional Gradient with Gradient Sliding for Composite Optimization", IJCAI'15.
  8. [ACML] with Yiu-ming Cheung, “Proximal Average Approximated Incremental Gradient Method for Composite Penalty Regularized Empirical Risk Minimization", ACML'15.