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。近年在NeurIPS、ICML、ACM CCS、IEEE S&P、ICCV、CVPR、SIGMOD、VLDB、WWW、IEEE TDSC等人工智能、数据库、安全与隐私保护领域的顶会顶刊上发表论文60余篇，并获得安全与隐私保护顶会ACM CCS 2024杰出论文奖(ACM SIGSAC Distinguished 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领域主席、AAAI资深程序委员，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。

邮箱：louj5@mail.sysu.edu.cn

个人主页：https://sites.google.com/view/jianlou

目前招收多名2026年入学的直博生与硕士生，依托学院可信大模型研究中心常年招收多名博士后，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！

 

研究与招生：

招生方向包括但不限于可信人工智能、可信大模型、人工智能隐私保护、数据治理与服务、数据质量评估、数据隐私保护等，重点研究如何利用数据治理、数据质量评估及隐私保护等理论与方法，确保人工智能和大模型在实际应用中具备可信性，符合社会伦理和法规要求，规避潜在风险与有害行为，同时保护数据提供者与模型使用者的隐私。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。

  • 欢迎有意攻读yl23455永利官网博士与硕士研究生的同学与我们联系，目前招收2026年9月入学的直博博士生1～2名与保研硕士生2名！

  • 欢迎有意来yl23455永利官网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。

 

学术服务：

领域主席(Area Chair)与资深程序委员(Senior PC Member): 人工智能顶会ICML 2024-2025, AAAI 2025

程序委员(PC Member): 信息安全顶会ACM CCS 2024-2025、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

 

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）：

  • with Chenyang Zhang*, Xiaoyu Zhang(张肖瑜), Kai Wu(吴凯), Zilong Wang(王子龙), Xiaofeng Chen(陈晓峰), “PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models", ICML'25 [CCF-A].
  • with Kejia Chen*, Jiawen Zhang*, Jiacong Hu, Yu Wang, Mingli Song(宋明黎), Zunlei Feng(冯尊磊), “Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models", ICML'25 [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 [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.
  • Hong kyu Lee, Qiuchen Zhang, Carl Yang, Jian Lou, Li Xiong, “Contrastive Unlearning: A Contrastive Approach to Machine Unlearning", IJCAI'25 [CCF-A].
  • Xiaoyu Zhang(张肖瑜), Yong Lin, Meixia Miao, Jian Lou, Jin Li(李进), Xiaofeng Chen(陈晓峰), “Zeroth-Order Federated Private Tuning for Pretrained Large Language Models", ACISP'25.
  • Xiaoyu Zhang(张肖瑜), Yulin Jin, Haoyu Tong, Jian Lou, Kai Wu(吴凯), Xiaofeng Chen(陈晓峰), “Purifier+ : Plug-and-play Backdoor Mitigation for Pre-trained Models via Activation Alignment", IEEE Transactions on Multimedia, 2025.
  • with Xiaoyu Zhang(张肖瑜), Chenyang Zhang*, Kai Wu(吴凯), Zilong Wang(王子龙), Xiaofeng Chen(陈晓峰), “DuplexGuard: Safeguarding Deletion Right in Machine Unlearning via Duplex Watermarking", IEEE Transactions on Dependable and Secure Computing, 2024 [CCF-A].
  • Haoyu Tong*, Xiaoyu Zhang(张肖瑜), Yulin Jin*, Jian Lou, Kai Wu(吴凯), Xiaofeng Chen(陈晓峰), “Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions", ACM MM'24 [CCF-A].
  • with Jiawen Zhang*, Kejia Chen*, Zunlei Feng(冯尊磊), Mingli Song(宋明黎), “SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models", ECAI'24.
  • Junxu Liu, Jian Lou, Li Xiong, Jinfei Liu(刘金飞), Xiaofeng Meng(孟小峰), “Cross-silo Federated Learning with Record-level Personalized Differential Privacy", ACM CCS'24 [CCF-A] (Distinguished Paper Award).
  • with Yuke Hu*, Jiaqi Liu*, et al., “ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach", ACM CCS'24 [CCF-A].
  • Wen Yin, Jian Lou, Pan Zhou(周潘), Yulai Xie(谢雨来), Dan Feng(冯丹), Yuhua Sun, Tailai Zhang, Lichao Sun, “Temperature-based Backdoor Attacks on Thermal Infrared Object Detection", CVPR'24 [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 [CCF-A].
  • Wenjie Wang, Pengfei Tang, Jian Lou, Yuanming Shao, Lance Waller, Yi-an Ko, Li Xiong, “IGAMT: Privacy Preserved Electronic Health Record Synthetic Approach with Heterogeneity and Irregularity", AAAI'24 [CCF-A].
  • Lanlan Chen, Kai Wu(吴凯), Jian Lou, Jing Liu, “Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics", AAAI'24.
  • with Hongwei Yao*, et al., “PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", S&P/Oakland'24 [CCF-A].
  • Hongwei Yao*, Jian Lou, Zhan Qin, “PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models", ICASSP'24.
  • Congcong Fu*, Hui Li(李辉), Jian Lou, Huizhen, Li, Jiangtao Cui(崔江涛), “DP-starJ: A Differentially Private Scheme towards Analytical Star-Join Queries", SIGMOD'24 [CCF-A].
  • with Jiaqi Liu*, et al., “Certified Minimax Unlearning with Generalization Rates and Deletion Capacity", NeurIPS'23 [CCF-A].
  • with Shuijing Zhang*, Li Xiong, Xiaoyu Zhang(张肖瑜), Jing Liu, “Closed-form Machine Unlearning for Matrix Factorization", CIKM'23.
  • Junxu Liu, Jian Lou, Li Xiong, Xiaofeng Meng(孟小峰), “Personalized Differentially Private Federated Learning without Exposing Privacy Budgets", CIKM'23.
  • Yulin Jin*, Xiaoyu Zhang(张肖瑜), Jian Lou, Xiaofeng Chen(陈晓峰), “ACQ: Few-shot Backdoor Defense via Activation Clipping and Quantizing", ACM MM'23 [CCF-A].
  • with Junxu Liu*, Mingsheng Xue*, Xiaoyu Zhang(张肖瑜), Li Xiong, Zhan Qin, “MUter: Machine Unlearning on Adversarial Training Models", ICCV'23 [CCF-A].
  • Yulin Jin*, Xiaoyu Zhang(张肖瑜), Jian Lou, Xu Ma, Xiaofeng Chen(陈晓峰), Zilong Wang(王子龙), “Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective", ICCV'23 [CCF-A].
  • Haocheng Xia, Jinfei Liu(刘金飞), Jian Lou, et al., “Equitable Data Valuation Meets the Right to be Forgotten in Model Markets", VLDB'23 [CCF-A].
  • Fereshteh Razmi, Jian Lou, Li Xiong, Yuan Hong, “Interpretation Attacks on Interpretable Models with Electronic Health Records", ECML-PKDD'23.
  • Yiling He*, Jian Lou, et al., “FINER: Enhancing State-of-the-art Classifiers with Feature  Attribution to Facilitate Risk Analysis", ACM CCS'23 [CCF-A].
  • Farnaz Tahmasebian*, Jian Lou, Li Xiong, “RobustFed: A Truth Inference Approach for Robust Federated Learning", CIKM'22.
  • Congcong Fu*, Hui Li(李辉), Jian Lou, Jiangtao Cui(崔江涛), “DP-HORUS: Differentially Private Hierarchical Count Histograms under Untrusted Server", CIKM'22.
  • with Xiaoyu Zhang(张肖瑜), Yulin Jin*, Tao Wang, Xiaofeng Chen(陈晓峰), “Purifier: Plug-and-play Backdoor Mitigation for Pre-trained Models Via Anomaly Activation Suppression", ACM MM'22 [CCF-A].
  • Junxu Liu*, Jian Lou, Li Xiong, Jinfei Liu(刘金飞), Xiaofeng Meng(孟小峰), “Projected Federated Averaging with Heterogeneous Differential Privacy", VLDB'22 [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 [CCF-A].
  • with Haowen Lin*, Li Xiong, Cyrus Shahabi, “Integer-arithmetic-only Certified Robustness for Quantized Neural Networks", ICCV'21 [CCF-A].
  • with Qiuchen Zhang*, Jing Ma*, Li Xiong, “Private Stochastic Non-convex Optimization with Improved Utility Rates", IJCAI'21 [CCF-A]. 
  • with Wenjie Wang*, Pengfei Tang*, Li Xiong, “Certified Robustness to Word Substitution Attack with Differential Privacy", NAACL'21.
  • with Jing Ma*, Qiuchen Zhang*, Li Xiong, Joyce Ho, “Communication Efficient Federated Generalized Tensor Factorization for Collaborative Health Data Analytics", WWW'21 [CCF-A].
  • Jinfei Liu(刘金飞), Jian Lou, Junxu Liu, Li Xiong, Jian Pei, Jimeng Sun, “Dealer: An End-to-End Model Marketplace with Differential Privacy", VLDB'21 [CCF-A].
  • Jing Ma*, Qiuchen Zhang*, Jian Lou, Li Xiong, Joyce Ho, Sivasubramanium Bhavani, “Communication Efficient Tensor Factorization for Decentralized Healthcare Networks", ICDM'21.
  • Jing Ma*, Qiuchen Zhang*, Jian Lou, Li Xiong, Joyce Ho, “Temporal Network Embedding via Tensor Factorization", CIKM'21.
  • 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.
  • with Yiu-ming Cheung, “Projection-free Online Empirical Risk Minimization with Privacy-preserving and Privacy Expiration", WI-IAT'20 (Best in Theoretical Paper Award).
  • with Yifei Ren*, Li Xiong, Joyce Ho, “Robust Irregular Tensor Factorization and Completion for Temporal Health Data Analysis", CIKM'20.
  • with Yiu-ming Cheung, “Robust Low-rank Tensor Minimization via a New Tensor Spectral k-Support Norm”, IEEE Transactions on Image Processing, 2020 [CCF-A].
  • Jing Ma*, Qiuchen Zhang*, Jian Lou, Joyce Ho, Li Xiong, Xiaoqian Jiang,“Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis", CIKM'19.
  • with Yiu-ming Cheung, "Uplink Communication Efficient Differentially Private Sparse Optimization With Feature-Wise Distributed Data", AAAI'18 [CCF-A].
  • with Yiu-ming Cheung, “Proximal Average Approximated Incremental Gradient Descent for Composite Penalty Regularized Empirical Risk Minimization”, Machine Learning, 2017.
  • with Yiu-ming Cheung, “Scalable Spectral k-Support Norm Regularization for Robust Low Rank Subspace Learning", CIKM'16.
  • with Yiu-ming Cheung, “Efficient Generalized Conditional Gradient with Gradient Sliding for Composite Optimization", IJCAI'15 [CCF-A].
  • with Yiu-ming Cheung, “Proximal Average Approximated Incremental Gradient Method for Composite Penalty Regularized Empirical Risk Minimization", ACML'15.