Publication

G, Mortensen,Genevieve*,  Zhu, R*. ADetectoLocum: Harnessing Locally Deployable LLMs for Early Alzheimer's Disease Detection Through Voice Analysis. (AMIA informatics summit 2025)

Zhang K, Zhu R, Ma S, Xiong J, Kim Y, Murai F, Liu X. Kedrec-lm: A knowledge-distilled explainable drug recommendation large language model  (NIP@IR Workshop)

Z Wang*, R Zhu*, Z Zhang, H Tang, X Wang. Rigging the Foundation: Manipulating Pre-training for Advanced Membership Inference Attacks (IEEE S&P)

Z Wang*, R Zhu*, Z Zhang, H Tang, X Wang. Sharpness-Aware Initialization: Improving Differentially Private Machine Learning from First Principles (USENIX Security)

Zhu, R., Tang, D., Tang, S., Wang, Z,. Tao, G., Ma, S., Wang, X., & Tang, H. Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering. (NDSS 2024)

Wang, Z.*, Zhu, R*, Zhou, D., Zhang, Z., Mitchell, J., Tang, H., & Wang, X. DPAdapter: Improving differentially private deep learning through noise tolerance pre-training (USENIX 2024). 

Chen, X.*, Tang, S.*, Zhu, R.*, Yan, S., Jin, L., Wang,. Z., Su, L., Wang, X., & Tang, H. (2023). The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks. (CCS 2024)

Li, Z.*, Zhu, R*, Ziahao, W., Haixu, T., & Hongfeng, C. Fairfix: Improving fairness of deep neural networks through selective amnesia and recovery. (Best Paper Award, SmartCom 2023)

Zhu, R., Tang, D., Tang, S., Wang, X., & Tang, H. (2023). Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models. IEEE Security and Privacy (IEEE S&P) 2023.

Li, X., Qin, Y., Zhu, R., Lin, T., Fan, Y., Kang, Y., Song, K., Zhao, F., Sun, C., Tang, H., & Liu, X. (2023). STINMatch: Semi-Supervised Semantic-Topological Iteration Network for Financial Risk Detection via News Label Diffusion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 9304-9315). Singapore: Association for Computational Linguistics.

Tang, D., Zhu, R., Wang, X., Tang, H., & Chen, Y. (2022). Understanding Impacts of Task Similarity on Backdoor Attack and Detection. arXiv preprint arXiv:2210.06509.

Li, X., Liu, K., Zhu, R., Kang, Y., Sun, C., Song, K., & Liu, X. (2022, December). Hierarchical Multi-task Learning for Enterprise Risk Detection from Financial Documents. In 2022 IEEE International Conference on Big Data (Big Data) (pp. 3505-3508). IEEE.

Zhu, R., Jiang, C., Wang, X., Wang, S., Zheng, H., & Tang, H. (2020). Privacy-preserving construction of generalized linear mixed model for biomedical computation. Intelligent Systems for Molecular Biology(ISMB) 2020

Zhu, R., Lin, B., & Tang, H. (2020). Bounding the number of linear regions in local area for neural networks with relu activations. arXiv preprint arXiv:2007.06803.