Smaug: Modular Augmentation of LLVM for MPC
Published:
This post is based on the paper Smaug: Modular Augmentation of LLVM for MPC.
이 글은 Smaug: Modular Augmentation of LLVM for MPC 논문을 기반으로 정리한 내용이다.
Deep Dives
Here I keep structured paper reviews, research reflections, and technical deep dives on papers I read.
Core Focus: Privacy-Preserving Machine Learning and Cryptography
This section contains detailed analyses of research papers related to my core interests. I focus on understanding how theoretical techniques such as homomorphic encryption, secure multi-party computation, and differential privacy are applied in real systems.
Each deep dive includes a structured breakdown of the paper’s motivation, methodology, key contributions, limitations, and potential research directions.
2026
NOISETTE: Certifying Differential Privacy Mechanisms Efficiently
Published:
This post is based on the paper NOISETTE: Certifying Differential Privacy Mechanisms Efficiently.
이 글은 NOISETTE: Certifying Differential Privacy Mechanisms Efficiently 논문을 기반으로 정리한 내용이다.
Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B
Published:
This post is based on the paper Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B.
이 글은 Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B 논문을 기반으로 정리한 내용이다.
2025
FedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks
Published:
This post is based on the paper FedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks.
이 글은 FedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks 논문을 기반으로 정리한 내용이다.
Federated Unlearning: Concept & Challenges
Published:
This post is based on the talk Learning and Unlearning Your Data in Federated Settings (PEPR ‘24, USENIX).
이 글은 Learning and Unlearning Your Data in Federated Settings 발표를 기반으로 정리한 내용이다.
MaskCRYPT: Federated Learning With Selective Homomorphic Encryption
Published:
This post is based on the paper MaskCRYPT: Federated Learning With Selective Homomorphic Encryption.
이 글은 MaskCRYPT: Federated Learning With Selective Homomorphic Encryption 논문을 기반으로 정리한 내용이다.
HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
Published:
This post is based on the paper HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption.
이 글은 HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption 논문을 기반으로 정리한 내용이다.