Yongqin Wang

Yongqin Wang

Senior Machine Learning Engineer @ Roblox

Yongqin Wang

I am a Senior Machine Learning Engineer at Roblox. I completed my PhD at the University of Southern California (USC) in 2026, advised by Prof. Murali Annavaram. My research interests are centered around privacy preserving mechanisms in the cloud setting. Specifically, I am interested in cloud applications that utilize ML models to process user data. Given the increasing prevalence of ML and the potential harm caused by data leakage from the cloud, my work aims to address these pressing concerns.

I have been working on Trusted Execution Environments (TEE), Oblivious RAM (ORAM), and Multi-Party Computing (MPC). You can find more about my research in my publications section and my Google Scholar. Feel free to connect with me on LinkedIn.

Publication Summary

  • [HPCA’26] Joongun Park, Yongqin Wang, Huan Xu, Hanjiang Wu, Mengyuan Li, Tushar Krishna, “SCALE: Tackling Communication Bottlenecks in Confidential Distributed Machine Learning”. [link]

  • [PETS’25] Christopher HK, Yongqin Wang, Rachit Rajat, Georg Carle, Murali Annavaram , “PIGEON: A High Throughput Framework for Private Inference of Neural Networks using Secure Multiparty Computation”. [link]

  • [PETS’25] Christopher HK, Ajith Suresh, Yongqin Wang, Hossein Yalame, Georg Carle, Murali Annavaram , “High-Throughput Secure Multiparty Computation with an Honest Majority in Various Network Settings”. [link]

  • [ASPLOS’24] Yongqin Wang, Rachit Rajat, Murali Annavaram, “MPC-Pipe: An Efficient Pipeline Scheme for Semi-honest MPC Machine Learning”. [link]
  • [ISCA’23] Yongqin Wang*, Rachit Rajat*, Murali Annavaram, “LAORAM: A Look Ahead ORAM Architecture for Training Large Embedding Tables”. [link]
  • [MICRO’22] Rachit Rajat, Yongqin Wang, Murali Annavaram, “PageORAM: An Efficient DRAM Page Aware ORAM Strategy”. [link]
  • [ISPASS’22] Yongqin Wang, Edward Suh, Wenjie Xiong, Benjamin Lefaudeux, Brian Knott, Murali Annavaram, Hsien-Hsin S. Lee “Characterization of MPC-based Private Inference for Transformer-based Models”. [link]
  • [MICRO’21] Hanieh Hashemi, Yongqin Wang, Murali Annavaram, “DarKnight: An accelerated framework for privacy and integrity preserving deep learning using trusted hardware”. [link]
  • [ICLR’21 Workshop] Hanieh Hashemi, Yongqin Wang, Murali Annavaram, “Byzantine-Robust and Privacy-Preserving Framework for FedML”. [link]
  • [CLOUD’21] Krishna Giri Narra, Zhifeng Lin, Yongqin Wang, Keshav Balasubramanian, Murali Annavaram, “Origami inference: Private inference using hardware enclaves”. [link]

* Equal contributions.

Pre-prints

  • Tingting Tang, James Flemings, Yongqin Wang, Murali Annavaram, Differentially Private Retrieval-Augmented Generation.
  • Tingting Tang, Yongqin Wang, Murali Annavaram, LRD-MPC: Efficient MPC Inference through Low-rank Decomposition.
  • Jonghyun Lee, Yongqin Wang, Rachit Rajat, Mengyuan Li, Murali Annavaram, Characterization of GPU TEE Overheads in Distributed Data Parallel ML Training. [link]
  • Yongqin Wang, Rachit Rajat, Jonghyun Lee, Tingting Tang, Murali Annavaram, Fastrack: Fast IO for Secure ML using GPU TEEs. [link]
  • Yongqin Wang, Pratik Sarkar, Nishat Koti, Arpita Patra, Murali Annavaram, CompactTag: Minimizing Computation Overheads in Actively-Secure MPC for Deep Neural Networks. [link]