Youyeon Joo
Portrait
Ph.D. student

This will be updated soon.

If you have any questions, please feel free to contact me.

E-mail Google Scholar GitHub LinkedIn ORCID
Education
  • Seoul National University
    Seoul National University
    Department of Electrical and Computer Engineering
    Ph.D. Student (Advisor: Yunheung Paek)
    Mar. 2022 - present
  • Ewha Womans University
    Ewha Womans University
    B.S. in Cyber Security (Cum Laude)
    Mar. 2018 - Feb. 2022
Experience
  • Yale University
    Yale University
    Visiting student
    Jun. 2023 - Jul. 2023
Honors & Awards
  • Excellence Paper Award of ASK 2026 (granted by KIPS)
    2026
  • Excellence Paper Award of ACK 2024 (granted by KIPS)
    2024
  • Excellence Paper Award of ASK 2023 (granted by KIPS)
    2023
  • Academic Excellence Scholarship (granted by Ewha Womans University)
    2020-2022
News
2026
"PCPSI: Efficient Unbalanced Private Set Intersection Using Homomorphic Encryption with Plaintext–Ciphertext Multiplication" is accepted to IEEE Access.
Jun 08
"I will serve on the Artifact Evaluation Committee (AEC) for CCS 2026 and NDSS 2027."
May 20
"HEPIC: Private Inference over Homomorphic Encryption with Client Intervention" is accepted to ASPLOS 2026.
Mar 22
2025
"An Accelerator for low-computational overhead Privacy-Preserving GNN Inference" is accepted to HiPC 2025.
Sep 12
"Efficient Keyset Design for Neural Networks Using Homomorphic Encryption" is accepted to MDPI Sensors.
Jul 08
Selected Publications (view all )
HEPIC: Private Inference over Homomorphic Encryption with Client Intervention

Kevin Nam, Youyeon Joo, Seungjin Ha, Hyungon Moon$\dagger$, Yunheung Paek$\dagger$ ($\dagger$ corresponding author)

ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2026

Recent HE-based Private Inference (PI) improve the accuracy-performance trade-off via a layer-wise scheme and parameter switching, yet remain bottlenecked by fire-and-forget execution in which the server alone performs costly ciphertext management. This paper presents HEPIC, an HE-based PI system that explores a new design point by leveraging client interventions for ciphertext managements.

[Paper]

HEPIC: Private Inference over Homomorphic Encryption with Client Intervention

Kevin Nam, Youyeon Joo, Seungjin Ha, Hyungon Moon$\dagger$, Yunheung Paek$\dagger$ ($\dagger$ corresponding author)

2026

Recent HE-based Private Inference (PI) improve the accuracy-performance trade-off via a layer-wise scheme and parameter switching, yet remain bottlenecked by fire-and-forget execution in which the server alone performs costly ciphertext management. This paper presents HEPIC, an HE-based PI system that explores a new design point by leveraging client interventions for ciphertext managements.

[Paper]

SLOTHE : Lazy Approximation of Non-Arithmetic Neural Network Functions over Encrypted Data

Kevin Nam*, Youyeon Joo*, Seungjin Ha, Yunheung Paek$\dagger$ (* equal contribution, $\dagger$ corresponding author)

USENIX Security Symposium (USENIX Sec), 2025

Existing works adopt an eager approximation (EA) strategy to approximate non-arithmetic functions (NAFs), which statically replaces each NAF with a fixed polynomial, locking in computational errors and limiting optimization opportunities. We propose SLOTHE, a lazy approximation (LA) solution that recursively decomposes NAF codes into arithmetic and nonarithmetic sub-functions, selectively approximating only the non-arithmetic components when required.

[Paper] [Code] [Zenodo]

SLOTHE : Lazy Approximation of Non-Arithmetic Neural Network Functions over Encrypted Data

Kevin Nam*, Youyeon Joo*, Seungjin Ha, Yunheung Paek$\dagger$ (* equal contribution, $\dagger$ corresponding author)

2025

Existing works adopt an eager approximation (EA) strategy to approximate non-arithmetic functions (NAFs), which statically replaces each NAF with a fixed polynomial, locking in computational errors and limiting optimization opportunities. We propose SLOTHE, a lazy approximation (LA) solution that recursively decomposes NAF codes into arithmetic and nonarithmetic sub-functions, selectively approximating only the non-arithmetic components when required.

[Paper] [Code] [Zenodo]

All publications