This will be updated soon.
If you have any questions, please feel free to contact me.
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
-
Seoul National UniversityDepartment of Electrical and Computer Engineering
Ph.D. Student (Advisor: Yunheung Paek)Mar. 2022 - present -
Ewha Womans UniversityB.S. in Cyber Security (Cum Laude)Mar. 2018 - Feb. 2022
Experience
-
Yale UniversityVisiting studentJun. 2023 - Jul. 2023
Honors & Awards
-
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
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) systems 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 different design point by leveraging client interventions for ciphertext managements.
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) systems 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 different design point by leveraging client interventions for ciphertext managements.
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.
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.