Publications
For the most up-to-date citation record, see my Google Scholar. My name is shown in bold below. Acceptance rates are shown where available.
Peer-Reviewed Publications
1.
SecDTD: Dynamic Token Drop for Secure Transformers Inference
Yifei Cai, Zhuoran Li, Yizhou Feng, Qiao Zhang, Hongyi Wu, Danella Zhao, and Chunsheng Xin.
IEEE European Symposium on Security and Privacy (EuroS&P), 2026.
2.
Towards Zero Rotation and Beyond: Architecting Neural Networks for Fast Secure Inference with Homomorphic Encryption
Yifei Cai, Yizhou Feng, Qiao Zhang, Chunsheng Xin, and Hongyi Wu.
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2026.
3.
DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
Xiaozuo Shen, Yifei Cai, Rui Ning, Chunsheng Xin, and Hongyi Wu.
International Conference on Machine Learning (ICML), PMLR 306:110706–110728, 2026.
4.
TAMI-MPC: Trusted Acceleration of Minimal-Interaction MPC for Efficient Nonlinear Inference
Zhuoran Li, Hanieh Totonchi Asl, Yifei Cai, Ebrahim Nouri, and Danella Zhao.
Design Automation Conference (DAC), 2026.
5.
Silentflow: Leveraging Trusted Execution for Resource-Limited MPC via Hardware-Algorithm Co-design
Zhuoran Li, Hanieh Totonchi Asl, Ebrahim Nouri, Yifei Cai, and Dan Zhao.
Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 737–743, 2026.
6.
MOSAIC: A Prune-and-Assemble Approach for Efficient Model Pruning in Privacy-Preserving Deep Learning
Yifei Cai, Qiao Zhang, Rui Ning, Chunsheng Xin, and Hongyi Wu.
ACM Asia Conference on Computer and Communications Security (AsiaCCS), pp. 1034–1048, 2024.
7.
TILE: Input Structure Optimization for Neural Networks to Accelerate Secure Inference
Yizhou Feng, Qiao Zhang, Yifei Cai, Hongyi Wu, and Chunsheng Xin.
Annual Computer Security Applications Conference (ACSAC), pp. 1203–1216, 2024.
8.
Privacy-Preserving Machine Learning as a Service: Challenges and Opportunities
Qiao Zhang, Tao Xiang, Yifei Cai, Zhichao Zhao, Ning Wang, and Hongyi Wu.
IEEE Network, 37(6):214–223, 2023.
9.
Hunter: HE-Friendly Structured Pruning for Efficient Privacy-Preserving Deep Learning
Yifei Cai, Qiao Zhang, Rui Ning, Chunsheng Xin, and Hongyi Wu.
ACM Asia Conference on Computer and Communications Security (AsiaCCS), pp. 931–945, 2022.
Preprints and Manuscripts
[P1]
DegreeSpar: Structured Degree Sparsity for Efficient Secure Transformer Inference
Yifei Cai, Zhuoran Li, Xiaozuo Shen, Hongyi Wu, and Chunsheng Xin.
arXiv preprint, under review, 2026.
[P2]
When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders
Xiaozuo Shen, Yifei Cai, Tian Tan, Rui Ning, Chunsheng Xin, and Hongyi Wu.
arXiv preprint, under review, 2026.
Dissertation
Towards Efficient Privacy-Preserving Deep Learning: HE-Friendly Structures, Flexible Pruning, HE-Efficient Architectures, and Secure Transformer Token Drop
Yifei Cai. Ph.D. Dissertation, Old Dominion University, 2025.