I am a Professor with the Department of Computer Science & Technology at Nanjing University. Prior to joining NJU, I worked at NEC Labs Princeton as a full-time Researcher. I was also a Visiting Researcher at Microsoft Research Asia. I earned my Ph.D. in Computer Science from the College of William and Mary, and received the Distinguished Dissertation Award in Natural and Computational Sciences.
My research interests span a broad range of emerging tech topics in the space of security, autonomy and mobility. I seek to explore computationally scientific discoveries with real-world impact and create disruptive innovations reshaping how people live. I am currently building trustworthy sustainable ubiquitous AI-Agent applications, with a focus on
LLM Agents for Security Tasks Automation
Privacy-Preserving Mobile AI-Copilot
Tools for Explainable AI & Decentralized AI
Dataset Preparation for Arbitrary Object Detection: An Automatic Approach based on Web Information in English
Shucheng Li, Boyu Chang, Bo Yang, Hao Wu, Sheng Zhong, and Fengyuan Xu.
The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. (SIGIR 2023)
Manipulating Transfer Learning for Property Inference
Yulong Tian, Fnu Suya, Anshuman Suri, Fengyuan Xu, and David Evans.
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023. (CVPR 2023)
LEAP: TrustZone Based Developer-Friendly TEE for Intelligent Mobile Apps
Lizhi Sun, Shuocheng Wang, Hao Wu, Yuhang Gong, Fengyuan Xu, Yunxin Liu, Hao Han, and Sheng Zhong.
IEEE Transactions on Mobile Computing. (TMC)
Privacy-Preserving and Robust Federated Deep Metric Learning
Yulong Tian, Xiaopeng Ke, Zeyi Tao, Shaohua Ding, Fengyuan Xu, Qun Li, Hao Han, Sheng Zhong, and Xinyi Fu.
2022 IEEE/ACM International Symposium on Quality of Service. (IWQoS 2022)
Towards Automated Safety Vetting of Smart Contracts in Decentralized Applications
Yue Duan, Xin Zhao, Yu Pan, Shucheng Li, Minghao Li, Fengyuan Xu, and Mu Zhang.
2022 ACM Conference on Computer and Communications Security. (CCS 2022) Best Paper Honorable Mention
DAPter: Preventing User Data Abuse in Deep Learning Inference Services
Hao Wu, Xuejin Tian, Yuhang Gong, Xing Su, Minghao Li, and Fengyuan Xu.
The 30th Web Conference. (WWW 2021)
PECAM: Privacy-Enhanced Video Streaming & Analytics via Securely-Recoverable Transformation
Hao Wu, Xuejin Tian, Minghao Li, Yunxin Liu, Ganesh Ananthanarayanan, Fengyuan Xu, and Sheng Zhong.
The 27th Annual International Conference On Mobile Computing And Networking. (MobiCom 2021a)
AsyMo: Scalable and Efficient Deep-Learning Inference on Asymmetric Mobile CPUs
Manni Wang*, Shaohua Ding*, Ting Cao, Yunxin Liu, and Fengyuan Xu.
The 27th Annual International Conference On Mobile Computing And Networking. (MobiCom 2021b) *co-first authors
EMO: Real-Time Emotion Recognition from Single-Eye Images for Resource-Constrained Eyewear Devices
Hao Wu, Jinghao Feng, Xuejin Tian, Edward Sun, Yunxin Liu, Bo Dong, Fengyuan Xu, and Sheng Zhong.
18th ACM International Conference on Mobile Systems, Applications, and Services. (MobiSys 2020)
Occlumency: Privacy-preserving Remote Deep-learning Inference Using SGX
Taegyeong Lee, Zhiqi Lin, Saumay Pushp, Caihua Li, Yunxin Liu, Youngki Lee, Fengyuan Xu, Chenren Xu, Junehwa Song, and Lintao Zhang.
25th ACM International Conference on Mobile Computing and Networking. (MobiCom 2019)
V-edge: Fast Self-constructive Power Modeling of Smartphones Based on Battery Voltage Dynamics
Fengyuan Xu, Yunxin Liu, Qun Li, and Yongguang Zhang.
The 10th USENIX Symposium on Networked Systems Design and Implementation. (NSDI 2013).
IMDGuard: Securing Implantable Medical Devices with the External Wearable Guardian
Fengyuan Xu, Zhengrui Qin, Chiu C. Tan, Baosheng Wang, and Qun Li.
The 30th IEEE International Conference on Computer Communications. (INFOCOM 2011)