한국정보처리학회:학술대회논문집 (Annual Conference of KIPS)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

동형암호를 적용한 CNN 추론을 위한 ReLU 함수 근사에 대한 연구

A Study on Approximation Methods for a ReLU Function in Homomorphic Encrypted CNN Inference

  • 주유연 (서울대학교 전기.정보공학부, 서울대학교 반도체공동연구소) ;
  • 남기빈 (서울대학교 전기.정보공학부, 서울대학교 반도체공동연구소) ;
  • 이동주 (서울대학교 전기.정보공학부, 서울대학교 반도체공동연구소) ;
  • 백윤흥 (서울대학교 전기.정보공학부, 서울대학교 반도체공동연구소)
  • You-yeon Joo (Dept. of Electrical and Computer Engineering and Inter-University Semiconductor Research Center(ISRC), Seoul National University) ;
  • Kevin Nam (Dept. of Electrical and Computer Engineering and Inter-University Semiconductor Research Center(ISRC), Seoul National University) ;
  • Dong-ju Lee (Dept. of Electrical and Computer Engineering and Inter-University Semiconductor Research Center(ISRC), Seoul National University) ;
  • Yun-heung Paek (Dept. of Electrical and Computer Engineering and Inter-University Semiconductor Research Center(ISRC), Seoul National University)
  • 발행 : 2023.05.18
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

As deep learning has become an essential part of human lives, the requirement for Deep Learning as a Service (DLaaS) is growing. Since using remote cloud servers induces privacy concerns for users, a Fully Homomorphic Encryption (FHE) arises to protect users' sensitive data from a malicious attack in the cloud environment. However, the FHE cannot support several computations, including the most popular activation function, Rectified Linear Unit (ReLU). This paper analyzes several polynomial approximation methods for ReLU to utilize FHE in DLaaS.

키워드

과제정보

This work was supported by the BK21 FOUR program of the Education and Research Program for Future ICT Pioneers, Seoul National University in 2023. This work was supported by Inter-University Semiconductor Research Center (ISRC). This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2023-2020-0-01602) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation) This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2022-0-00516, Derivation of a Differential Privacy Concept Applicable to National Statistics Data While Guaranteeing the Utility of Statistical Analysis)