Towards Practical Oblivious Relational Analytics with Heterogeneous TEE
S&P '27To appearHowdy! This is Weijie Huang (黄炜杰, pronounces “Way-Jee(-eh) Hwahng”).
I am a Ph.D. student in Computer Science at Indiana University Bloomington, supervised by Prof. Haixu Tang and Prof. Chenghong Wang (previously Prof. XiaoFeng Wang). I was previously a Ph.D. student at Rice University with Dr. Nathan Dautenhahn advising me.
My research interests lie at the intersection of:
- system security and trusted execution environments (TEEs),
- high-performance computing, with a recent focus on securing and optimizing LLM infrastructures,
- program analysis and least-privilege principles,
- agentic security & privacy.
I obtained my B.Eng. degree in Computer Science and Engineering at Southern University of Science and Technology in 2022. It was a great time working with Prof. Fengwei Zhang.
Recent Publications
All publicationsHoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture
CCS '26@inproceedings{du2026hoss,
title = {Hoss: Fast Oblivious Semantic Search with Heterogeneous {GPU-CPU-TEE} Architecture},
author = {Du, Jianzhang and Huang, Weijie and Wang, Chenghong and Tsagareli, Nicolas and Luo, Yukui and Wang, XiaoFeng and Gu, Zhongshu},
booktitle = {Proceedings of the 2026 ACM SIGSAC Conference on Computer and Communications Security},
series = {CCS '26},
pages = {152--166},
publisher = {ACM},
year = {2026},
doi = {10.1145/3830454.3846673}
}Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree
arXiv@misc{zhao2026large,
title = {Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree},
author = {Zhao, Leyi and Huang, Weijie and Guo, Yitong and Bian, Jiang and Wang, Chenghong and Zhang, Xuhong},
year = {2026},
eprint = {2601.14523},
archivePrefix = {arXiv},
doi = {10.48550/arXiv.2601.14523}
}