Yujin Nam

Ph.D. Candidate in Computer Science, UC San Diego

About Me

I’m a Ph.D. candidate in the Computer Science and Engineering department at University of California, San Diego, working at the System Energy Efficiency Lab (SEE Lab) with Professor Tajana Simunic Rosing.

My research focuses on building secure and privacy-preserving machine learning systems. I work on fully homomorphic encryption, secure ML inference and training, encrypted federated learning, private retrieval, hyperdimensional computing, and GPU/system optimization for encrypted computation.

I am currently looking for research scientist, research engineer, and ML/systems engineering roles in trustworthy AI and privacy-preserving infrastructure. Feel free to reach out at yujinnam@ucsd.edu.

Publications

FHEmem: A Processing In-Memory Accelerator for Fully Homomorphic Encryption

Zhou, M., Nam, Y., Gangwar, P., Xu, W., Dutta, A., Wilkerson, C., Cammarota, R., et al.

IEEE Transactions on Emerging Topics in Computing, 2025

DOI

Rhychee-FL: Robust and Efficient Hyperdimensional Federated Learning with Homomorphic Encryption

Nam, Y., Moitra, A., Venkatesha, Y., Yu, X., De Micheli, G., Wang, X., Zhou, M., et al.

2025 Design, Automation & Test in Europe Conference (DATE)

DOI

PATHE: A Privacy-Preserving Database Pattern Search Platform with Homomorphic Encryption

Wang, X., Zhou, M., De Micheli, G., Nam, Y., Pinge, S., Vega, A., Rosing, T.

2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)

DOI

PATHE: A Privacy-Preserving Mass Spectrometry Database Pattern Search Platform with Fully Homomorphic Encryption

Wang, X., Zhou, M., Nam, Y., De Micheli, G., Pinge, S., Vega, A., Rosing, T.

2025 ACM/IEEE Design Automation Conference (DAC)

UFC: A Unified Accelerator for Fully Homomorphic Encryption

Zhou, M., Nam, Y., Wang, X., Lee, Y., Wilkerson, C., Kumar, R., Taneja, S., et al.

2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO)

DOI

GraSS: Graph-based Similarity Search on Encrypted Query

Kim, D., Nam, Y., Wang, W., Gong, H., Bhati, I., Cammarota, R., Rosing, T.S., et al.

Cryptology ePrint Archive, 2024

ePrint

HEaaN-STAT: A Privacy-Preserving Statistical Analysis Toolkit for Large-Scale Numerical, Ordinal, and Categorical Data

Lee, Y., Seo, J., Nam, Y., Chae, J., Cheon, J.H.

IEEE Transactions on Dependable and Secure Computing (TDSC), 2024

DOI

Efficient Host Intrusion Detection using Hyperdimensional Computing

Nam, Y., King, R., Burke, Q., Zhou, M., McDaniel, P., Rosing, T.

2024 IEEE International Conference on Big Data – CyberHunt Workshop

DOI

MatHE: A Near-Mat Processing In-Memory Accelerator for Fully Homomorphic Encryption

Zhou, M., Nam, Y., Gangwar, P., Xu, W., Dutta, A., Wilkerson, C., Cammarota, R., et al.

2024 ACM/IEEE Design Automation Conference (DAC)

Efficient Machine Learning on Encrypted Data Using Hyperdimensional Computing

Nam, Y., Zhou, M., Gupta, S., De Micheli, G., Cammarota, R., Wilkerson, C., Micciancio, D., Rosing, T.

2023 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)

DOI

Hardware Architecture of a Number Theoretic Transform for a Bootstrappable RNS-based Homomorphic Encryption Scheme

Kim, S., Lee, K., Cho, W., Nam, Y., Cheon, J.H., Rutenbar, R.A.

2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)

DOI

Education

University of California, San Diego

Ph.D in Computer Science; GPA: 3.9/4.0

2021 - present

Seoul National University (SNU)

B.S. in Electrical and Computer Engineering, Cum Laude; GPA: 3.80/4.30

2015 - 2020

Research and Engineering Experience

UC San Diego, Yale, IBM

Graduate Researcher – Privacy-Preserving Federated Learning

Jun 2023 – Sep 2024

Designed an FHE and hyperdimensional computing framework for privacy-preserving model aggregation. Built and evaluated a secure federated learning pipeline under communication, computation, and ciphertext-representation constraints. Analyzed CKKS parameters, ciphertext packing, and model representation trade-offs. Published at DATE 2025.

Intel Labs / UC San Diego

Graduate Research Intern – Private Similarity Search

Jun 2023 – Sep 2023

Designed a privacy-preserving retrieval system for graph-based search over encrypted queries. Developed encrypted graph operations for traversal, neighbor selection, set operations, and top-k retrieval. Built PET primitives including blind rotation, encrypted set intersection/union, and oblivious sorting.

UC San Diego

Graduate Researcher – Encrypted Hyperdimensional Computing

Nov 2021 – Apr 2023

Designed and evaluated FHE-based machine learning algorithms using hyperdimensional computing. Investigated CKKS parameters, ciphertext packing layouts, multiplicative depth, and SIMD-style batching for encrypted training and inference. Published at ISLPED 2023.

Intel Corp. / UC San Diego

Graduate Research Intern – FHE Workload Acceleration

Jun 2022 – Sep 2022

Designed and implemented privacy-preserving ML workloads using fully homomorphic encryption. Analyzed ciphertext multiplication, rotation, key switching, and bootstrapping-related operations. Contributed to accelerator-oriented performance modeling for GPU-oriented FHE computation.

Crypto Lab Inc.

Researcher – Privacy-Preserving Analytics and FHE Acceleration

Aug 2019 – Oct 2020

Developed a CKKS-based statistical analysis toolkit for privacy-preserving computation over numerical, ordinal, and categorical data. Designed ciphertext data layouts and packing strategies for efficient large-scale secure analytics. Contributed to NTT hardware accelerator design for RNS-based CKKS homomorphic encryption.

Honors and Awards

  • National Scholarship for Science and Engineering, Korea Student Aid Foundation (fully funded), 2017 – 2019
  • SNU Merit-Based Scholarship, Seoul National University, 2015 and 2016