CREMON: Cryptography Embedded on the Convolutional Neural Network Accelerator

Yeongjae Choi; Jaehyeong Sim; Lee Sup Kim

doi:10.1109/TCSII.2020.2971580

CREMON: Cryptography Embedded on the Convolutional Neural Network Accelerator

Yeongjae Choi
, Jaehyeong Sim
, Lee Sup Kim

Department of Computer Science & Engineering

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

Abstract

Due to their excellent performance, tremendous progress has been made in the development of convolutional neural network (CNN) algorithms and efficient CNN accelerators for edge devices. At the same time, security concerns about CNN processing have increased regarding user privacy and safety. In this brief, we focus on developing an efficient data ciphering system embedded in a CNN accelerator. The number of operations of CNN and security workloads, AES-128 in our system, constantly changes during execution, thereby varying their relative ratio. To efficiently support various convolution/AES workloads, we propose CREMON, a reconfigurable system with a cryptography reconfigurable processing element (CRPE). A test chip with the proposed scheme was implemented and tested for performance verification. As a result, the CREMON prototype chip achieved state-of-the-art performance/area efficiency for AES and improved energy efficiency by up to 44.1% in processing CNN/AES workloads.

Original language	English
Article number	8981800
Pages (from-to)	3337-3341
Number of pages	5
Journal	IEEE Transactions on Circuits and Systems II: Express Briefs
Volume	67
Issue number	12
DOIs	https://doi.org/10.1109/TCSII.2020.2971580
State	Published - Dec 2020

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation of Korea grant funded by the Korea Government (MSIP) under Grant NRF-2017R1A2B2009380, and in part by the Samsung Advanced Institute of Technology.

Publisher Copyright:
© 2004-2012 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

AES hardware
CNN accelerator
Security in CNN processing
energy-efficient hardware
reconfigurable processor

Access to Document

10.1109/TCSII.2020.2971580

Cite this

@article{f8a4d39e27084db7be40cd413f7c6a4d,

title = "CREMON: Cryptography Embedded on the Convolutional Neural Network Accelerator",

abstract = "Due to their excellent performance, tremendous progress has been made in the development of convolutional neural network (CNN) algorithms and efficient CNN accelerators for edge devices. At the same time, security concerns about CNN processing have increased regarding user privacy and safety. In this brief, we focus on developing an efficient data ciphering system embedded in a CNN accelerator. The number of operations of CNN and security workloads, AES-128 in our system, constantly changes during execution, thereby varying their relative ratio. To efficiently support various convolution/AES workloads, we propose CREMON, a reconfigurable system with a cryptography reconfigurable processing element (CRPE). A test chip with the proposed scheme was implemented and tested for performance verification. As a result, the CREMON prototype chip achieved state-of-the-art performance/area efficiency for AES and improved energy efficiency by up to 44.1\% in processing CNN/AES workloads.",

keywords = "AES hardware, CNN accelerator, Security in CNN processing, energy-efficient hardware, reconfigurable processor",

author = "Yeongjae Choi and Jaehyeong Sim and Kim, \{Lee Sup\}",

note = "Funding Information: This work was supported in part by the National Research Foundation of Korea grant funded by the Korea Government (MSIP) under Grant NRF-2017R1A2B2009380, and in part by the Samsung Advanced Institute of Technology. Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2020",

month = dec,

doi = "10.1109/TCSII.2020.2971580",

language = "English",

volume = "67",

pages = "3337--3341",

journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",

issn = "1549-7747",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - CREMON

T2 - Cryptography Embedded on the Convolutional Neural Network Accelerator

AU - Choi, Yeongjae

AU - Sim, Jaehyeong

AU - Kim, Lee Sup

N1 - Funding Information: This work was supported in part by the National Research Foundation of Korea grant funded by the Korea Government (MSIP) under Grant NRF-2017R1A2B2009380, and in part by the Samsung Advanced Institute of Technology. Publisher Copyright: © 2004-2012 IEEE.

PY - 2020/12

Y1 - 2020/12

N2 - Due to their excellent performance, tremendous progress has been made in the development of convolutional neural network (CNN) algorithms and efficient CNN accelerators for edge devices. At the same time, security concerns about CNN processing have increased regarding user privacy and safety. In this brief, we focus on developing an efficient data ciphering system embedded in a CNN accelerator. The number of operations of CNN and security workloads, AES-128 in our system, constantly changes during execution, thereby varying their relative ratio. To efficiently support various convolution/AES workloads, we propose CREMON, a reconfigurable system with a cryptography reconfigurable processing element (CRPE). A test chip with the proposed scheme was implemented and tested for performance verification. As a result, the CREMON prototype chip achieved state-of-the-art performance/area efficiency for AES and improved energy efficiency by up to 44.1% in processing CNN/AES workloads.

AB - Due to their excellent performance, tremendous progress has been made in the development of convolutional neural network (CNN) algorithms and efficient CNN accelerators for edge devices. At the same time, security concerns about CNN processing have increased regarding user privacy and safety. In this brief, we focus on developing an efficient data ciphering system embedded in a CNN accelerator. The number of operations of CNN and security workloads, AES-128 in our system, constantly changes during execution, thereby varying their relative ratio. To efficiently support various convolution/AES workloads, we propose CREMON, a reconfigurable system with a cryptography reconfigurable processing element (CRPE). A test chip with the proposed scheme was implemented and tested for performance verification. As a result, the CREMON prototype chip achieved state-of-the-art performance/area efficiency for AES and improved energy efficiency by up to 44.1% in processing CNN/AES workloads.

KW - AES hardware

KW - CNN accelerator

KW - Security in CNN processing

KW - energy-efficient hardware

KW - reconfigurable processor

UR - https://www.scopus.com/pages/publications/85097066971

U2 - 10.1109/TCSII.2020.2971580

DO - 10.1109/TCSII.2020.2971580

M3 - Article

AN - SCOPUS:85097066971

SN - 1549-7747

VL - 67

SP - 3337

EP - 3341

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

IS - 12

M1 - 8981800

ER -

CREMON: Cryptography Embedded on the Convolutional Neural Network Accelerator

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this