미리보기
기본 정보
반갑읍니다.
기술 스택
Python, Git, CUDA, C++, Rust, 알고리즘, 아키텍처, 암호학, Java, JavaScript
경력
엠즈푸드시스템
대리 | GOT
2019.09. ~ 2021.01. (1년 5개월)
수요예측 시스템의 구축 및 데이터 분석
CERN
researcher | openlab
2021.01. ~ 2021.12. (1년)
QKD 시뮬레이터
Homomorphic Encryption 시스템 구축
Quatum Computing을 활용한 GAN
Desilo
Research Engineer | Research | 재직 중
2021.12. ~ 재직 중 (3년 3개월)
Homomorphic Encryiton Library 연구 및 개발
프로젝트
Quantumacy
CERN
2021.01. ~ 2021.12.
This is the official repository of the Quantumacy project, for more information check our website.
Content
QKDSimkit is a simulator for quantum key distribution, it allows to exchange symmetric keys, there are two different interfaces: peer-to-peer and client-server; QKDSimkit
Fork of Openfl that integrates QKDSimkit in its transport protocol; openfl-develop
Some of the deep learning models we used in our use cases, for example, chestscan is used in openfl-develop; dl_models
The Homomorphic Encryption Inference Use Case proposes an innovative setup where a two-fold quantum resilient encryption setup (QKD + Homomorphic Encryption) is used for privacy-preserving machine learning inference. It is based on 3 entities, client, storage, and server (processing). homomorphic-encryption-use-case
Liberate.FHE
Desilo
2022.01. ~ 2023.11.
Liberate.FHE is an open-source Fully Homomorphic Encryption (FHE) library for bridging the gap between theory and practice with a focus on performance and accuracy.
Liberate.FHE is designed to be user-friendly while delivering robust performance, high accuracy, and a comprehensive suite of convenient APIs for developing real-world privacy-preserving applications.
Liberate.FHE is a pure Python and CUDA implementation of FHE. So, Liberate.FHE supports multi-GPU operations natively.
The main idea behind the design decisions is that non-cryptographers can use the library; it should be easily hackable and integrated with more extensive software frameworks.
Additionally, several design decisions were made to maximize the usability of the developed software:
Make the number of dependencies minimal.
Make the software easily hackable.
Set the usage of multiple GPUs as the default.
Make the resulting library easily integrated with the pre-existing software, especially Artificial Intelligence (AI) related ones.
교육
아주대
대학원(석사) | 데이터사이언스
2017.09. ~ 2019.08. | 졸업
외국어
영어
비즈니스 회화 가능
일본어
일상 회화 가능
프랑스어
일상 회화 가능