Miran Kim's research mainly focuses on Privacy-Enhancing Cryptography (PEC), which aims to develop advanced cryptographic primitives to protect sensitive data of individuals. In particular, she has been actively working on the development of homomorphic encryption, which enables to compute any function on encrypted data without decryption. Also, she has been working on privacy-preserving protocols in a wide range of applications such as data query processing, genomic analysis, and machine learning.

김미란 연구실의 연구는 주로 개인의 민감한 데이터를 보호하기 위한 고급 암호화 기본 요소를 개발하는 것을 목표로 하는 프라이버시 강화 암호화(PEC)에 중점을 둡니다. 특히, 그녀는 암호화된 데이터를 복호화하지 않고도 모든 함수를 계산할 수 있는 동형 암호화 개발에 적극적으로 참여해 왔습니다. 또한, 데이터 쿼리 처리, 유전체 분석, 머신러닝과 같은 광범위한 응용 분야에서 프라이버시 보호 프로토콜에 대해 연구하고 있습니다.

More Efficient Lattice-based OLE from Circuit-private Linear HE with Polynomial Overhead

Empowering AI with Privacy through Homomorphic Encryption for Secure Deep Reinforcement Learning

THOR: Secure Transformer Inference with Homomorphic Encryption

Descriptor: Benchmarking Secure Neural Network Evaluation Methods for Protein Sequence Classification (iDASH24)

Finding Highly Similar Regions of Genomic Sequences Through Homomorphic Encryption

Accelerating HE Operations from Key Decomposition Technique

COLLAGENE enables privacy-aware federated and collaborative genomic data analysis

Secure Human Action Recognition by Encrypted Neural Network Inference

Privacy-aware Estimation of Relatedness in Admixed Populations

The Evolving Privacy and Security Concerns for Genomic Data Analysis and Sharing as Observed from the iDASH Competition

Evaluation of Vicinity-based Hidden Markov Models for Genotype Imputation

SVAT: Secure Outsourcing of Variant Annotation and Genotype Aggregation

Trusted Monitoring Service

Introduction to Homomorphic Encryption and Schemes

Ultra-Fast Homomorphic Encryption Models enable Secure Outsourcing of Genotype Imputation

Efficient Homomorphic Conversion Between (Ring) LWE Ciphertexts

Open Imputation Server Provides Secure Imputation Services with Provable Genomic Privacy

Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning

Homomorphic Computation of Local Alignment

A Secure System for Genomics Clinical Decision Support

Semi-Parallel Logistic Regression for GWAS on Encrypted Data

SCOR: A secure international informatics infrastructure to investigate COVID-19

Secure and Differentially Private Bayesian Learning on Distributed Data

Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference

Secure and Differentially Private Logistic Regression for Horizontally Distributed Data

SecureLR: Secure Logistic Regression Model via a Hybrid Cryptographic Protocol

Secure Outsourced Matrix Computation and Application to Neural Networks

A Full RNS Variant of Approximate Homomorphic Encryption

Bootstrapping for Approximate Homomorphic Encryption

Logistic Regression Model Training based on the Approximate Homomorphic Encryption

Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation

Homomorphic Encryption for Arithmetic of Approximate Numbers

A Standard API FOR RLWE-based Homomorphic Encryption

Secure Searching of Biomarkers Using Hybrid Homomorphic Encryption Scheme

Encrypting Controller using Fully Homomorphic Encryption for Security of Cyber-Physical Systems

Optimized Search-and-Compute Circuits and Their Application to Query Evaluation on Encrypted Data

HEALER: Homomorphic computation of ExAct Logistic rEgRession for secure rare disease variants analysis in GWAS

Search-and-Compute on Encrypted Data

Homomorphic Computation of Edit Distance

Private Genome Analysis through Homomorphic Encryption

Homomorphic encryption for arithmetic of approximate numbers

A full rns variant of approximate homomorphic encryption

Secure outsourced matrix computation and application to neural networks

Secure logistic regression based on homomorphic encryption: design and evaluation

Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference

Logistic regression model training based on the approximate homomorphic encryption

Private genome analysis through homomorphic encryption

Homomorphic computation of edit distance

Encrypting controller using fully homomorphic encryption for security of cyber-physical systems

HEALER: homomorphic computation of ExAct Logistic rEgRession for secure rare disease variants analysis in GWAS

Efficient homomorphic conversion between (ring) LWE ciphertexts

Ultrafast homomorphic encryption models enable secure outsourcing of genotype imputation

Search-and-compute on encrypted data

Optimized search-and-compute circuits and their application to query evaluation on encrypted data

Secure and differentially private logistic regression for horizontally distributed data

Secure human action recognition by encrypted neural network inference

Semi-parallel logistic regression for GWAS on encrypted data

THOR: Secure transformer inference with homomorphic encryption

We present a new and efficient method to obtain circuit privacy for lattice-based linearly homomorphic encryptions (LHE). In particular, our method does not involve noise-flooding with exponetially large errors or iterative bootstrapping. As a direct result, we obtain a semi-honest oblivious linear evaluation (OLE) protocol with the same efficiency, reducing the communication cost of the prior state of the art by 50%. 
Consequently, the amortized time of our protocol improves the prior work by 33% under 100Mbps network setting. Our semi-honest OLE is the first to achieve both concrete efficiency and asymptotic quasi-optimality. Together with an extension of the recent zero-knowledge proof of plaintext knowledge, our LHE yields actively-secure OLE with 2.7x reduced communication from the prior work. When applied to Overdrive (Eurocrypt '18), an MPC preprocessing protocol, our method provides 1.4x improvement in communication over the state of the art.

Miran Kim

Associate Professor

Miran Kim Lab

교수님 소개

Miran Kim

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

More Efficient Lattice-based OLE from Circuit-private Linear HE with Polynomial Overhead

Empowering AI with Privacy through Homomorphic Encryption for Secure Deep Reinforcement Learning

THOR: Secure Transformer Inference with Homomorphic Encryption

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

Miran Kim

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

More Efficient Lattice-based OLE from Circuit-private Linear HE with Polynomial Overhead

Empowering AI with Privacy through Homomorphic Encryption for Secure Deep Reinforcement Learning

THOR: Secure Transformer Inference with Homomorphic Encryption

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집