Xiangrui Xu

Xiangrui Xu is an Assistant Professor in Department of EECS at South Dakota State University. His research focuses on applied cryptography, private inference, secure multi-party computation, edge computing, and systems security, with a particular interest in building efficient privacy-preserving protocols for real-world machine learning and AI systems. He received his Ph.D. Computer Science @ Old Dominion University (working closely with Dr. Hongyi Wu and Dr. Chunsheng Xin). His broader academic interests include applied cryptography, hardware-software co-design, and the systems aspects of trustworthy AI.

I am currently recruiting PhD students and multiple research interns for 27Spring/Fall in South Dakota State Uni, Feel free to contact me via email attaching your CV, transcripts and relevant docs with email subject: [PhD Applicant] Name - University - MS/BS

News

2026. 6 Invited to give a talk at Boston University (host: Dr. Mayank Varia)
2026. 5 I will serve as CCS 26, NDSS 27 and FAST 27 artifacts program committee. Welcome to submit your papers.
2026. 5 Congrats to Dr. Wang for completing her defense!
2026. 4 One paper about secure protocol is accepted by Trans on services computing! Right before my defense😃
2026. 4 Passed my PhD Defense. 🎉 Officially a Dr. Xu now!🥳🥳
2026. 3 give a talk at New Mexico Tech.
2026. 2 give a talk at Cal State Uni Northridge.
2025. 10 I have been invited as TPC in ICNC 2026🥳
2025. 9 One paper about robust personalized FL accepted by The Journal of Supercomputing🥳
2025. 8 One paper about model compression for private inference accepted by TMLR 🥳
2025. 8 Invited to give a lightning talk at SysteMPC'25👍
2025. 6 One paper accepted by Computer Networks🎉
2025. 5-8 I will intern at SD solutions. LLC. as AI/Cyber Research Intern🎉 Thank you SD solutions.
2025. 1 Two papers accepted by Neurocomputing and Computer Communications
2024. 11 One paper about fast private Transformer inference is online.🌟
2024. 7 One paper about private inference on mobile computing accepted by ICDCS 🧡

Research

Parallel Inference Acceleration

🚀 Designed parallel inference pipelines for privacy-preserving MLaaS, reducing latency on edge devices
⚡ Achieved ~60% faster inference with overlap scheduling and pipelining techniques
⚙️ collaborated with PyTorch + CUDA kernels, scalable to cloud deployment
☁️ Demonstrated edge-to-cloud efficiency, bridging research and real-world deployment

Xu, X. et al. SPOT: Structure Patching and Overlap Tweaking for Effective Pipelining in Privacy-Preserving MLaaS with Tiny Clients. 2024 ICDCS.
Xu, J., Guan, C., & Xu, X. (2018). Energy-efficiency for smartphones using interaction link prediction in mobile cloud computing. CCF Conference on Computer Supported Cooperative Work and Social Computing.

Efficient Model Architecture

☁️Clear out long-standing rumor in related research

🏗️ Developed quantization-friendly network linearization for secure inference
📉 Reduced communication overhead by ~50% without loss of accuracy
⚙️ Optimized LLM and vision model architectures for edge and cloud deployment
🔐 Enabled model compression with minimal performance trade-offs

Xu, X. et al (2025). PrivShap: A Finer-granularity Network Linearization Method for Private Inference. TMLR

Efficient Secure Protocol

🔐 Designed secure and communication-efficient transformer inference protocols
📉 Reduced communication cost by ~60% while maintaining model accuracy
🚀 Improved throughput & latency for large-scale privacy-preserving inference
☁️ Applied to LLMaaS and enterprise secure AI platforms, bridging research to deployment

Xu, X. et al (2024a). Comet: A communication-efficient and performant approximation for private transformer inference. ArXiv Preprint ArXiv:2405.17485.
X. Xu, Q. Zhang, R. Ning, C. Xin, and H. Wu, LUTless: Local Initial Approximation for Secure Power Function in Private Machine Learning, in IEEE Transactions on Services Computing (TSC), 2026.

Robust Efficient Distributed Training

⚡ Built resilient federated learning frameworks with dynamic trust adaptation and Byzantine robustness
🤝 Developed personalized collaboration mechanisms for heterogeneous clients
🔄 Introduced anti-forgetting strategies for incremental model updates
☁️ Enabled robust and efficient distributed training across cloud and edge environments

Bai, Y., Wang, Y., Xu, X., Yang, Y., Batool, H., Iqbal, Z., & Xu, J. (2025). AsyncDefender: Dynamic trust adaptation and collaborative defense for Byzantine-robust asynchronous federated learning. Computer Networks, 111430.
Wang, Y., Xu, J., Yuan, Q., Bai, Y., Yang, Y., Xu, X., & Batool, H. (2025). Fgcfl: a fine-grained clustering framework for federated learning with heterogeneity data. J. Supercomput., 81(14), 1328.
Xu, J., Zhao, Y., Li, X., Zhou, L., Zhu, K., Xu, X., Duan, Q., & Zhang, R. (2025). Teg-di: Dynamic incentive model for federated learning based on tripartite evolutionary game. Neurocomputing, 621, 129259.
Xu, J., Zhou, L., Zhao, Y., Li, X., Zhu, K., Xu, X., Duan, Q., & Zhang, R. (2025). A two-stage federated learning method for personalization via selective collaboration. Computer Communications, 232, 108053.
Zhu, K., Xu, J., Zhou, L., Li, X., Zhao, Y., Xu, X., & Li, S. (2025). Dmaf: data-model anti-forgetting for federated incremental learning. Cluster Computing, 28(1), 30.

Publications

2026

X. Xu, Q. Zhang, R. Ning, C. Xin, and H. Wu, LUTless: Local Initial Approximation for Secure Power Function in Private Machine Learning, in IEEE Transactions on Services Computing (TSC), 2026. [Paper]
Yang, Y., Xu, X., Wang, Y., Bai, Y., Duan, Q., Xu, J., & Li, S. (2026). HierFedEHN: A hierarchical training framework for hypernetwork-based personalized federated learning. Computer Networks, 112379.

2025

Wang, Y., Xu, J., Yuan, Q., Bai, Y., Yang, Y., Xu, X., & Batool, H. (2025). Fgcfl: a fine-grained clustering framework for federated learning with heterogeneity data. J. Supercomput., 81(14), 1328.
Bai, Y., Wang, Y., Xu, X., Yang, Y., Batool, H., Iqbal, Z., & Xu, J. (2025). AsyncDefender: Dynamic trust adaptation and collaborative defense for Byzantine-robust asynchronous federated learning. Computer Networks, 111430.
Xu, X., Wang, Z., Ning, R., Xin, C., & Wu, H. (2025). PrivShap: A Finer-granularity Network Linearization Method for Private Inference. TMLR [Code] [Paper]
Xu, J., Zhao, Y., Li, X., Zhou, L., Zhu, K., Xu, X., Duan, Q., & Zhang, R. (2025). Teg-di: Dynamic incentive model for federated learning based on tripartite evolutionary game. Neurocomputing, 621, 129259.
Xu, J., Zhou, L., Zhao, Y., Li, X., Zhu, K., Xu, X., Duan, Q., & Zhang, R. (2025). A two-stage federated learning method for personalization via selective collaboration. Computer Communications, 232, 108053.
Zhu, K., Xu, J., Zhou, L., Li, X., Zhao, Y., Xu, X., & Li, S. (2025). Dmaf: data-model anti-forgetting for federated incremental learning. Cluster Computing, 28(1), 30.

2024

Xu, X., Zhang, Q., Ning, R., Xin, C., & Wu, H. (2024a). Comet: A communication-efficient and performant approximation for private transformer inference. ArXiv Preprint ArXiv:2405.17485.
Xu, X., Zhang, Q., Ning, R., Xin, C., & Wu, H. (2024b). SPOT: Structure Patching and Overlap Tweaking for Effective Pipelining in Privacy-Preserving MLaaS with Tiny Clients. 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS), 1318–1329. [Coverage] [Slides] [Paper] [Code]

2023 & before

Garcia, K. R., Ammons, J., Xu, X., & Chen, J. (2023). Phishing in social media: Investigating training techniques on Instagram shop. Proceedings of the Human Factors and Ergonomics Society Annual Meeting (HFES), 67(1), 1850–1855.
Xu, J., Guan, C., & Xu, X. (2018). Energy-efficiency for smartphones using interaction link prediction in mobile cloud computing. CCF Conference on Computer Supported Cooperative Work and Social Computing, 517–526.

Reviewer: TNNLS, Information Science, CVPR 25, ICCV 25, ICLR 25, NeurIPS 2025 ER Workshop, TMLR, TDSC, TMC, IEEE Network

TPC: ICNC 2026

Course

26 Fall: Mobile Cloud Computing

Page updated

Google Sites

Report abuse