Publication

ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack
In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
Yuanwei Wu#, Lingdong Huang, Yunlong Mao*, Kanye Ye WANG, Jingyu Hua*, Sheng Zhong*

PDF Bibtex

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
Zi Li#, Tian Zhou#, Wenze Li#, Jingyu Hua*, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks
In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
Yisheng Li#, Dongming Han, Hongkun Pan, Bingcheng Mao, Zijian Wang#, Yunlong Mao*, Wei Tong*, Sheng Zhong*

PDF Bibtex

FL-MPS: Secure Federated LLM Fine-Tuning via Adaptive Parameter Split and Efficient Negotiation
In IEEE Transactions on Dependable and Secure Computing, 2026
Yuejuan Zhu#, Yunlong Mao*, Guanzhi Qiu#, Shijie Ding#, Wenjun Qian, Sheng Zhong*

PDF Bibtex

SPA: Stealthy and Persistent Backdoor Attacks in Federated Learning via Feature-Space Alignment
In IEEE Transactions on Information Forensics and Security, 2026
Chengcheng Zhu#, Ye Li, Bosen Rao, Yunlong Mao*, Jiale Zhang, Tingting Wu, Xin Ge, Sheng Zhong*

PDF Bibtex

COVERT: Privacy-Preserving Covariant Obfuscation for VLMaaS via Exact Reparameterization and Tailored Tuning
In Proceedings of the 19th European Conference on Computer Vision (ECCV), 2026
Wenqiang Ruan, Zirui Huang#, Yu Lin, Qizhi Zhang, Yunlong Mao*, Quanwei Cai, Jue Hong, Sheng Zhong*, and Ye Wu

PDF Bibtex Slides

Designing Interface Interventions Against Address Poisoning Attacks in Web3 Wallets
In Proceedings of the 2026 ACM Symposium on User Interface Software and Technology (UIST), 2026
Yuqi Xu#, Maggie Yongqi Guan, Yunlong Mao*, Xin Yi, Wei Tong*, Sheng Zhong*, Xiaobo Zhou, and Kanye Ye Wang

PDF Bibtex

Designing Wallet-Based User Intervention for Approval Phishing Mitigation
In Proceedings of the 35th USENIX Security Symposium (Security), 2026
Maggie Yongqi Guan, Yuqi Xu#, Yunlong Mao*, Wei Tong*, Xiaobo Zhou and Kanye Ye Wang

PDF Bibtex

Liquidity Mining as an Attack Surface: Incentive-Induced Liquidity Attacks in Concentrated Liquidity Market Makers
In Proceedings of the 35th USENIX Security Symposium (Security), 2026
Sinong Lu, Chon Kit Lao, Yunlong Mao*, Xiaobo Zhou, Ruizhe Jia, and Kanye Ye Wang

PDF Bibtex

Preventing Dataset Misuse in Stable Diffusion for Multi-User Sharing
In Proceedings of the 2026 IEEE International Conference on Multimedia and Expo (ICME), 2026
Yubo Zhu#, Xinyue Zhao#, Zijian Wang#, Wei Tong*, Yunlong Mao*, and Sheng Zhong*

PDF Bibtex

Understanding the Parental Involvement in Their Children's Programming Learning
In Proceedings of the 24th EUSSET Conference on Computer Supported Cooperative Work (ECSCW), 2026
Janice Jianing Si, Xin Lin, Alicia Wanyi Liu, Shuhao Huang, Yujun Zhu, Caishi Huang, Yunlong Mao*, Xiaobo Zhou and Kanye Ye Wang

PDF Bibtex

Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
In Proceedings of the 33rd ACM Conference on Computer and Communications Security (CCS), 2026
Zirui Huang#, Yunlong Mao*, Wei Tong*, Tingting Wu, Xin Ge, and Sheng Zhong*

PDF Bibtex Code Slides

Counselors' Experiences of Privacy and Care in Anonymous Gambling Helplines
In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (UbiComp/IMWUT), 2026
Molly Zhuangtong Huang, Jingjie Li, Siohong Teng, Yunlong Mao*, Sheng Zhong*, Xiaobo Zhou and Kanye Ye Wang

PDF Bibtex

Fend for Yourself! Backdoor Purification in Federated Graph Learning with an Evolving Knowledge Anchor
In Proceedings of the 35th USENIX Security Symposium (Security), 2026
Chengcheng Zhu#, Yunlong Mao*, Jiale Zhang, Bosen Rao and Sheng Zhong*

PDF Bibtex Code Slides

ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks
In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL main), 2025
Yu Lin, Ruining Yang, Yunlong Mao*, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan and Sheng Zhong*

PDF Bibtex

SAP: Privacy-Preserving Fine-Tuning on Language Models with Split-and-Privatize Framework
In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025
Xicong Shen, Yang Liu, Yi Liu, Peiran Wang, Huiqi Liu, Jue Hong, Bing Duan, Zirui Huang#, Yunlong Mao*, Ye Wu, and Sheng Zhong*

PDF Bibtex

LT-OAQ: Learnable Threshold Based Outlier-aware Quantization And Its Energy-efficient Accelerator For Low-precision On-chip Training
In Design, Automation and Test in Europe Conference (DATE), 2025
Qinkai Xu#, Yijin Liu, Yuan Meng, Yang Chen, Yunlong Mao*, Li Li*, and Yuxiang Fu*

PDF Bibtex

CrossNet: A Low-Latency MLaaS Framework for Privacy-Preserving Neural Network Inference on Resource-Limited Devices
In IEEE Transactions on Dependable and Secure Computing, 2024
Yu Lin#, Tianling Zhang#, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

UBA-Inf: Unlearning Activated Backdoor Attack with Influence-Driven Camouflage
In Proceedings of the 33rd USENIX Security Symposium (Security), 2024
Zirui Huang#, Yunlong Mao*, Sheng Zhong*

PDF Bibtex Code Slides

Secure Model Aggregation against Poisoning Attacks for Cross-silo Federated Learning with Robustness and Fairness
In IEEE Transactions on Information Forensics & Security, 2024
Yunlong Mao*, Zhujing Ye#, Xinyu Yuan#, Sheng Zhong*

PDF Bibtex

Solution Probing Attack Against Coin Mixing Based Privacy-Preserving Crowdsourcing Platforms
In IEEE Transactions on Dependable and Secure Computing, 2024
Yunlong Mao*, Ziqin Dang#, Heng Wang#, Yuan Zhang*, Sheng Zhong*

PDF Bibtex

Unbalanced private set intersection with linear communication complexity
In Science China Information Sciences, 2024
Quanyu Zhao#, Bingbing Jiang#, Yuan Zhang*, Heng Wang#, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

Towards Universal Detection of Adversarial Examples via Pseudorandom Classifiers
In IEEE Transactions on Information Forensics & Security, 2023
Boyu Zhu#, Changyu Dong, Yuan Zhang*, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

A Comprehensive Study of Trajectory Forgery and Detection in Location-Based Services
In IEEE Transactions on Mobile Computing, 2023
Huaming Yang#, Zhongzhou Xia#, Zexi Xin#, Jingyu Hua*, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attacks
In Proceedings of the 28th European Symposium on Research in Computer Security (ESORICS), 2023
Yunlong Mao*, Zexi Xin#, Zhenyu Li, Jue Hong, Qingyou Yang, Sheng Zhong*

PDF Bibtex Slides

FLSwitch: Towards Secure and Fast Model Aggregation for Federated Deep Learning with a Learning State-Aware Switch
In Proceedings of the 21st International Conference on Applied Cryptography and Network Security (ACNS), 2023
Yunlong Mao*, Ziqin Dang#, Yu Lin#, Tianling Zhang#, Yuan Zhang*, Jingyu Hua*, Sheng Zhong*

PDF Bibtex Slides

Are you moving as you claim: GPS Trajectory Forgery and Detection in Location-Based Services
In Proceedings of the 42nd IEEE International Conference on Distributed Computing Systems (ICDCS), 2022
Huaming Yang#, Zhongzhou Xia#, Zexi Xin#, Jingyu Hua*, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

Solution Probing Attack Against Blockchain-based Quality-Aware Crowdsourcing Platforms
In Proceedings of the 19th IEEE International Conference on Mobile Ad Hoc and Smart Systems (MASS), 2022
Heng Wang#, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

Secure Deduplication Schemes for Content Delivery in Mobile Edge Computing
In Computers & Security, 2022
Yu Lin#, Yunlong Mao*, Yuan Zhang*, Sheng Zhong*

PDF Bibtex

Secure Deep Neural Network Models Publishing Against Membership Inference Attacks Via Training Task Parallelism
In IEEE Transactions on Parallel and Distributed Systems, 2021
Yunlong Mao*, Wenbo Hong#, Boyu Zhu#, Zhifei Zhu#, Yuan Zhang*, Sheng Zhong*

PDF Bibtex

Romoa: Robust Model Aggregation for the Resistance of Federated Learning to Model Poisoning Attacks
In Proceedings of the 26th European Symposium on Research in Computer Security (ESORICS), 2021
Yunlong Mao*, Xinyu Yuan#, Xinyang Zhao#, Sheng Zhong*

PDF Bibtex

Privacy-Preserving Computation Offloading for Parallel Deep Neural Networks Training
In IEEE Transactions on Parallel and Distributed Systems, 2020
Yunlong Mao*, Wenbo Hong#, Heng Wang#, Qun Li, Sheng Zhong*

PDF Bibtex

Private Deep Neural Network Models Publishing for Machine Learning as a Service
In IEEE/ACM 28th International Symposium on Quality of Service (IWQoS), 2020
Yunlong Mao*, Boyu Zhu#, Wenbo Hong#, Zhifei Zhu#, Yuan Zhang*, Sheng Zhong*

PDF Bibtex

Secure TDD MIMO Networks Against Training Sequence Based Eavesdropping Attack
In IEEE Transactions on Mobile Computing, 2019
Yunlong Mao*, Ying He#, Yuan Zhang*, Jingyu Hua*, Sheng Zhong*

PDF Bibtex

Towards Thwarting Template Side-channel Attacks in Secure Cloud Deduplications
In IEEE Transactions on Dependable and Secure Computing, 2019
Yuan Zhang*, Yunlong Mao*, Minze Xu#, Fengyuan Xu*, Sheng Zhong*

PDF Bibtex

Learning from Differentially Private Neural Activations with Edge Computing
In the Third ACM/IEEE Symposium on Edge Computing, 2018
Yunlong Mao*, Shanhe Yi, Qun Li, Jinghao Feng#, Fengyuan Xu*, Sheng Zhong*

PDF Bibtex

A Privacy-Preserving Deep Learning Approach for Face Recognition with Edge Computing
In USENIX Workshop on Hot Topics in Edge Computing (HotEdge), 2018
Yunlong Mao*, Shanhe Yi, Qun Li, Jinghao Feng#, Fengyuan Xu*, Sheng Zhong*

PDF Bibtex Slides

Location privacy in public access points positioning: An optimization and geometry approach
In Computers & Security, 2018
Yunlong Mao*, Yuan Zhang*, Xiaoyan Zhang, Fengyuan Xu*, Sheng Zhong*

PDF Bibtex

Towards Privacy-Preserving Aggregation for Collaborative Spectrum Sensing
In IEEE Transactions on Information Forensics & Security, 2017
Yunlong Mao*, Tingting Chen, Yuan Zhang*, Tiancong Wang#, Sheng Zhong*

PDF Bibtex

Joint Differentially Private Gale–Shapley Mechanisms for Location Privacy Protection in Mobile Traffic Offloading Systems
In IEEE Journal on Selected Areas in Communications, 2016
Yuan Zhang*, Yunlong Mao*, Sheng Zhong*

PDF Bibtex

Stemming Downlink Leakage from Training Sequences in Multi-User MIMO Networks
In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS), 2016
Yunlong Mao*, Yuan Zhang*, Sheng Zhong*

PDF Bibtex Slides

Privacy Preserving Distributed Permutation Test
In Proceedings of the 4th ACM International Workshop on Security in Cloud Computing, 2016
Yunlong Mao*, Yuan Zhang*

PDF Bibtex

Privacy Preserving Market Schemes for Mobile Sensing
In Proceedings of the 44th International Conference on Parallel Processing (ICPP), 2015
Yuan Zhang*, Yunlong Mao*, He Zhang#, Sheng Zhong*

PDF Bibtex

Protecting Location Information in Collaborative Sensing of Cognitive Radio Networks
In Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM), 2015
Yunlong Mao*, Tingting Chen, Yuan Zhang*, Tiancong Wang#, Sheng Zhong*

PDF Bibtex

Toward Wireless Security without Computational Assumptions—Oblivious Transfer Based on Wireless Channel Characteristics
In IEEE Transactions on Computers, 2014.
Zhuo Hao, Yunlong Mao*, Sheng Zhong*, Li Erran Li, Haifan Yao, Nenghai Yu

PDF Bibtex

Publications

# and * indicate student authors and faculty authors, respectively.