• Review of KIISC
• /
• v.27 no.3
• /
• pp.33-41
• /
• 2017

기계 학습(machine-learning) 분야의 분류 알고리즘(classification algorithms)은 의료 진단, 유전자 정보 해석, 스팸 탐지, 얼굴 인식 및 신용 평가와 같은 다양한 응용 서비스에서 사용되고 있다. 이와 같은 응용 서비스에서의 분류 알고리즘은 사용자의 민감한 정보를 포함하는 데이터를 이용하여 학습을 수행하는 경우가 많으며, 분류 결과도 사용자의 프라이버시와 연관된 경우가 많다. 따라서 학습에 필요한 데이터의 소유자, 응용 서비스 사용자, 그리고 서비스 제공자가 서로 다른 보안 도메인에 존재할 경우, 프라이버시 보호 문제가 발생할 수 있다. 본 논문에서는 이러한 문제를 해결하면서도 분류 서비스를 제공할 수 있도록 도와주는 프라이버시 보존 분류 프로토콜(privacy-preserving classification protocol: PPCP) 에 대해 소개한다. 구체적으로 PPCP의 프라이버시 보호 요구사항을 분석하고, 기존의 연구들이 프라이버시 보호를 위해 사용하는 암호학적 기본 도구(cryptographic primitive)들에 대해 소개한다. 최종적으로 그러한 암호학적 기본 도구를 사용하여 설계된 프라이버시 보존 분류 프로토콜에 대한 기존 연구들을 소개하고 분석한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.861-868
• /
• 2023

One of the key technologies in providing data analysis in the deep learning while maintaining security is fully homomorphic encryption. Due to constraints in operations on fully homomorphically encrypted data, non-arithmetic functions used in deep learning must be approximated by polynomials. Until now, the degrees of approximation polynomials with composite minimax polynomials have been uniformly set across layers, which poses challenges for effective network designs on fully homomorphic encryption. This study theoretically proves that setting different degrees of approximation polynomials constructed by composite minimax polynomial in each layer does not pose any issues in the inference on convolutional neural networks.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.291-298
• /
• 2024

Despite its wide application, cloud computing raises privacy leakage concerns because users should send their private data to the cloud. Homomorphic encryption (HE) can resolve the concerns by allowing cloud servers to compute on encrypted data without decryption. However, due to the huge computation overhead of HE, simply executing an entire cloud program with HE causes significant computation. Manually partitioning the program and applying HE only to the partitioned program for the cloud can reduce the computation overhead. However, the manual code partitioning and HE-transformation are time-consuming and error-prone. This work proposes a new homomorphic encryption enabled annotation-guided code partitioning compiler, called Heapa, for privacy preserving cloud computing. Heapa allows programmers to annotate a program about the code region for cloud computing. Then, Heapa analyzes the annotated program, makes a partition plan with a variable list that requires communication and encryption, and generates a homomorphic encryptionenabled partitioned programs. Moreover, Heapa provides not only two region-level partitioning annotations, but also two instruction-level annotations, thus enabling a fine-grained partitioning and achieving better performance. For six machine learning and deep learning applications, Heapa achieves a 3.61 times geomean performance speedup compared to the non-partitioned cloud computing scheme.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.161-164
• /
• 2022

Homomorphic Encryption (HE) schemes have been recently growing as a reliable solution to preserve users' information owe to maintaining and operating the user data in the encrypted state. In addition to that, several Neural Networks models merged with HE schemes have been developed as a prospective tool for privacy-preserving machine learning. Those mentioned works demonstrated that it is possible to match the accuracy of non-encrypted models but there is always a trade-off in the computation time. In this work, we evaluate the implementation of CKKS HE scheme operations over the layers of a LeNet5 convolutional inference model, however, owing to the limitations of the evaluation environment, the scope of this work is not to develop a complete LeNet5 encrypted model. The evaluation was performed using the MNIST dataset with Microsoft SEAL (MSEAL) open-source homomorphic encryption library ported version on Python (PyFhel). The behavior of the encrypted model, the limitations faced and a small description of related and future work is also provided.