Yewei Guan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yewei Guan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Hua Guo
Beihang University
2 shared publications - Jiarong Huo
School of Cyber Science and Technology, Beihang University, Beijing, China
2 shared publications Guo Hua
1 shared publication- Jin Tan
Ant Group, Shanghai, China
1 shared publication Liu Weiwei
1 shared publication- Weixin Liu
School of Cyber Science and Technology, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 24 April 2026
- Published by Springer Nature
- p. 507-527
Unbalanced Secret Labeled Private Set Intersection via Scalable Dual-Load Bloom Filter
- 24 April 2026
- Published by Springer Nature
- p. 507-527
Unbalanced Secret Labeled Private Set Intersection via Scalable Dual-Load Bloom Filter
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 3481-3482
Cryptanalysis of “Multi-Party Private Set Intersection With One-Round Online Interaction”
In this letter, we identify critical vulnerabilities in both protocols proposed by Zhao et al. (published in IEEE TIFS, doi: 10.1109/TIFS.2025.3574993), showing that they are susceptible to collusion attacks. In the first protocol, the leader P1 can determine whether its items are held by any honest party by colluding with other participants. In the second protocol, P1 can infer whether all honest parties hold a specific item without any collusion, violating the fundamental privacy guarantees of multi-party private set intersection.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 3481-3482
Cryptanalysis of “Multi-Party Private Set Intersection With One-Round Online Interaction”
In this letter, we identify critical vulnerabilities in both protocols proposed by Zhao et al. (published in IEEE TIFS, doi: 10.1109/TIFS.2025.3574993), showing that they are susceptible to collusion attacks. In the first protocol, the leader P1 can determine whether its items are held by any honest party by colluding with other participants. In the second protocol, P1 can infer whether all honest parties hold a specific item without any collusion, violating the fundamental privacy guarantees of multi-party private set intersection.
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (4) , 2038-2046
East: Efficient and Accurate Secure Inference Framework for Transformer
Transformer has been successfully used in practical applications due to its powerful advantages. However, users' input is leaked to the model provider during the service. With people's attention to privacy, privacy-preserving Transformer inference is on the demand of such services. Secure protocols for non-linear functions are crucial in privacy-preserving Transformer inference, which are not well studied. Thus, designing practical secure protocols for non-linear functions is hard but significant to model performance. In this work, we propose a framework East to enable efficient and accurate secure Transformer inference. Firstly, we propose a new oblivious piecewise polynomial evaluation algorithm and apply it to the activation functions, which reduces the runtime and communication of GELU by over 1.5× and 2.5×, compared to prior arts. Secondly, the secure protocols for softmax and layer normalization are carefully designed to faithfully maintain the desired functionality. Thirdly, several optimizations are conducted in detail to enhance the overall efficiency. We applied East to BERT and the results show that the inference accuracy remains consistent with the plaintext inference without fine-tuning. Compared to Iron, we achieve about 1.8× lower communication within 1.2× lower runtime.
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (4) , 2038-2046
East: Efficient and Accurate Secure Inference Framework for Transformer
Transformer has been successfully used in practical applications due to its powerful advantages. However, users' input is leaked to the model provider during the service. With people's attention to privacy, privacy-preserving Transformer inference is on the demand of such services. Secure protocols for non-linear functions are crucial in privacy-preserving Transformer inference, which are not well studied. Thus, designing practical secure protocols for non-linear functions is hard but significant to model performance. In this work, we propose a framework East to enable efficient and accurate secure Transformer inference. Firstly, we propose a new oblivious piecewise polynomial evaluation algorithm and apply it to the activation functions, which reduces the runtime and communication of GELU by over 1.5× and 2.5×, compared to prior arts. Secondly, the secure protocols for softmax and layer normalization are carefully designed to faithfully maintain the desired functionality. Thirdly, several optimizations are conducted in detail to enhance the overall efficiency. We applied East to BERT and the results show that the inference accuracy remains consistent with the plaintext inference without fine-tuning. Compared to Iron, we achieve about 1.8× lower communication within 1.2× lower runtime.