Shandong UniversityI'm Jinyu Lu(卢劲宇), a B.E. candidate at Shandong University.
My main research interests are Machine Learning, Privacy Computing, Computer Architecture, Quantization for Large Language Models and AI-Generated Content.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Shandong UniversitySoftware Engineering (Emerging Engineering Honors Program in Cyberspace Security)
B.E. StudentSep. 2022 - present -
Shanghai Jiao Tong UniversityComputer and Big Data Technology
Admitted, Enrolling Soon
Honors & Awards
-
First Prize of Outstanding Student Award of Shandong University2023.09
-
First Prize of Special Talent Award of Shandong University2023.09
-
Second Prize in the 15th National Mathematics Competition for University Students2023.12
-
Second Prize of C/C++ Programming in the 15th Blue Bridge Cup Shandong Competition (University Group A)2024.04
-
Second Prize of Outstanding Student Award of Shandong University2024.09
-
First Prize of Outstanding Student Award of Shandong University2025.09
-
Second Prize of Special Talent Award of Shandong University2025.09
-
Outstanding Graduates of Shandong University2026.01
News
Selected Publications (view all )
Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji, Fanyu Kong*, Guoqiang Yang (* equal contribution)
International Conference On Intelligent Computing (ICIC). 2025 [CCF C]
We propose a novel verifiable privacy-preserving scheme tailored for CNN convolutional layers, which achieves speedups ranging $26\times$ ~ $87\times$ compared to the original plaintext model while maintaining accuracy.
Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji, Fanyu Kong*, Guoqiang Yang (* equal contribution)
International Conference On Intelligent Computing (ICIC). 2025 [CCF C]
We propose a novel verifiable privacy-preserving scheme tailored for CNN convolutional layers, which achieves speedups ranging $26\times$ ~ $87\times$ compared to the original plaintext model while maintaining accuracy.
Secure Distributed Document Representation Outsourcing Scheme for Natural Language Processing in Cloud Computing
Jinyu Lu, Xinrong Sun, Yunting Tao, Fanyu Kong*, Chunpeng Ge, Hanlin Zhang (* equal contribution)
IEEE Transactions on Cloud Computing (TCC).Under review. 2024 [CCF B]
We propose a secure and verifiable distributed document representation outsourcing scheme based on the FBoW model in cloud computing. This scheme employs a novel blind method based on orthogonal symmetric matrices to preserve privacy and minimize computational overhead, achieving a 95.42% improvement in performance.
Secure Distributed Document Representation Outsourcing Scheme for Natural Language Processing in Cloud Computing
Jinyu Lu, Xinrong Sun, Yunting Tao, Fanyu Kong*, Chunpeng Ge, Hanlin Zhang (* equal contribution)
IEEE Transactions on Cloud Computing (TCC).Under review. 2024 [CCF B]
We propose a secure and verifiable distributed document representation outsourcing scheme based on the FBoW model in cloud computing. This scheme employs a novel blind method based on orthogonal symmetric matrices to preserve privacy and minimize computational overhead, achieving a 95.42% improvement in performance.