Dr.Anxiao Song

Assistant Professor Master Supervisor

Email:axsong@cityu.edu.mo

Academic Qualifications

2022 Ph.D. in Computer Science and Technology, Xidian University, China

2019 B.Eng. in Software Engineering, Henan University of Technology, China

Research Interests:

Privacy-Preserving Computing

Large Language Model (LLM) Security

Research & Publications:

[1] Song, A., Cheng, K., Fu, J., Cui, S., Zhang, T., Chang, Z., & Shen, Y. (2025). Private learning for vertical decision trees: A secure, accurate, and fast realization. IEEE Transactions on Dependable and Secure Computing. https://doi.org/10.1109/TDSC.2025.3579742

[2] Song, A., Cui, S., Cheng, K., Bai, J., Wang, Q., Lai, S., Russello, G., & Shen, Y. (2026). FSS-DT: Secure division-free decision tree training and inference via function secret sharing. IEEE Transactions on Dependable and Secure Computing. https://doi.org/10.1109/TDSC.2026.3695949

[3] Song, A., Cui, S., Bai, J., Cheng, K., Shen, Y., & Russello, G. (2025). Guard-GBDT: Efficient privacy-preserving approximated GBDT training on vertical dataset. In Proceedings of the International Symposium on Research in Attacks, Intrusions, and Defenses (RAID 2025).

[4] Song, A., Li, H., Cheng, K., Zhang, T., Sun, A., & Shen, Y. (2024). Guard-FL: An UMAP-assisted robust aggregation for federated learning. IEEE Internet of Things Journal, 11(16), 27557–27570. https://doi.org/10.1109/JIOT.2024.3399259

[5] Song, A., Zhang, T., Cheng, K., Cao, Y., Zhu, X., & Shen, Y. (2025). Byzantine-robust federated learning framework via a server-client defense mechanisms. IEEE Internet of Things Journal, 12(14), 29073–29088. https://doi.org/10.1109/JIOT.2025.3568443

[6] Zhang, T., Song, A., Dong, X., Shen, Y., & Ma, J. (2022). Privacy-preserving asynchronous grouped federated learning for IoT. IEEE Internet of Things Journal, 9(7), 5511–5523. https://doi.org/10.1109/JIOT.2021.3111088

[7] Cheng, K., Xia, Y., Song, A., Fu, J., Qu, W., Shen, Y., & Zhang, J. (2025). Mosformer: Maliciously secure three-party inference framework for large transformers. In Proceedings of the 32nd ACM Conference on Computer and Communications Security (CCS 2025).