Publications

Highlighted Conferences & Journals

Junxu Liu*, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng.
Cross-silo Federated Learning with Record-level Personalized Differential Privacy.
ACM Conference on Computer and Communications Security (CCS). 2024. (🏆 Distinguished Paper Award)
Junxu Liu*, Mingsheng Xue*, Jian Lou#, Xiaoyu Zhang, Li Xiong, and Zhan Qin.
MUter: Machine Unlearning on Adversarially Trained Models.
International Conference on Computer Vision (ICCV), 2023, pp. 4892-4902.
Junxu Liu*, Jian Lou, Li Xiong, and Xiaofeng Meng#.
Personalized Differentially Private Federated Learning without Exposing Privacy Budgets.

International Conference on Information and Knowledge Management (CIKM), 2023, pp. 4140-4144.

Junxu Liu*, Jian Lou, Li Xiong, Jinfei Liu, and Xiaofeng Meng#.
Projected Federated Averaging with Heterogeneous Differential Privacy.
International Conference on Very Large Data Bases (VLDB), 2022, 15(4), pp.828-840.
Junxu Liu* and Xiaofeng Meng#.
Survey on Privacy-preserving Machine Learning (in Chinese).
Journal of Computer Research and Development, 2020, 57(2), pp. 346-362. (Top 10 Most Cited Papers in 2020)

Other Conferences & Journals

Kun Fang, Qinghua Tao, Junxu Liu, Yaxin Xiao, Yulin Jin, Qingqing Ye, Jian Sun, Haibo Hu
Machine Unlearning in Low-Dimensional Feature Subspace
The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), accepted to appear, 2026.
Qiheng Sun, Junxu Liu, Xiaokai Mao, Haocheng Xia, Jinfei Liu, Kui Ren, Haibo Hu
Feature Attribution in Directed Acyclic Graphs Using Edge Intervention
IEEE International Conference on Data Engineering (ICDE), accepted to appear, 2027.
Qiheng Sun, Hongwei Zhang, Junxu Liu, Xiaokai Mao, Jinfei Liu, Kui Ren, Haibo Hu
DaDaDa: A Dataset for Data Pricing in Data Marketplaces
IEEE International Conference on Data Engineering (ICDE), accepted to appear, 2027.
Jiazheng Song, Junxu Liu, Jian Lou, Jinfei Liu
SafeAdapt: Safety Alignment with Adaptive Thinking Allocation for Large Reasoning Models
USENIX Security Symposium, 2026, pp. 4385-4404.
Li Bai, Junxu Liu, Sen Zhang, Xinwei Zhang, Qingqing Ye, Haibo Hu
United We Defend: Collaborative Membership Inference Defenses in Federated Learning
USENIX Security Symposium, 2026, pp. 1967--1986.
Mengyu Sun, Ziyuan Yang, Andrew Beng Jin Teoh, Junxu Liu, Haibo Hu, Yi Zhang
LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models
International Joint Conference on Artificial Intelligence (IJCAI), 2026.
Qiheng Sun, Hongwei Zhang, Junxu Liu, Haocheng Xia, Jinfei Liu, Kui Ren, Haibo Hu
Efficient Cooperation-Aware Key and Value Management for LLM Inference
International Conference on Very Large Data Bases (VLDB), 2026.
Pengyun Zhu, Qiheng Sun, Long Wen, Yanbo Wang, Yang Cao, Junxu Liu, Deyi Xiong, Jinfei Liu, Zhibo Wang, Kui Ren
APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation
ACL 2026 Main Conference, 2026.
Yuemin Zhang, Qingqing Ye, Junxu Liu, Wei Dong
Answering Federated Range Queries with Local Differential Privacy
IEEE International Conference on Data Engineering (ICDE), 2026.
Tairan Huang, Yulin Jin, Junxu Liu, Qingqing Ye, Haibo Hu
SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
Zitong Li, Qingqing Ye, Haibo Hu, Xin Huang, Junxu Liu, Xiaofeng Meng.
SUGPT: Efficient Graph Unsummarization for the Right to Be Forgotten.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2026.
Shiyu Zhang, Qingqing Ye, Junxu Liu, Kai Huang, Yulian Mao, Xinyue Sun, Wei Dong, Haibo Hu.
RATR: Optimized Trajectory Release with Temporal Local Differential Privacy
IEEE Transactions on Dependable and Secure Computing (TDSC), 2025.
Jinfei Liu*, Jian Lou, Junxu Liu, Li Xiong, Jian Pei, and Jimeng Sun
Dealer: an End-to-End Model Marketplace with Differential Privacy.
International Conference on Very Large Data Bases (VLDB), 2021, 14(6), pp. 957-969.