효과적인 딥러닝 기반 비프로파일링 부채널 분석 모델 설계방안
Design of an Effective Deep Learning-Based Non-Profiling Side-Channel Analysis Model
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
최근 딥러닝 기반 비프로파일링 부채널 분석이 제안됐다. 딥러닝 기반 비프로파일링 분석은 신경망 모델을 모든 추측키에 대해 학습시킨 뒤, 학습된 정도의 차이를 통해 올바른 비밀키를 찾아내는 기법이다. 이때, 신경망 학습모델 설계에따라 비프로파일링 분석성능이 크게 달라지기 때문에 올바른 모델 설계의 기준이 필요하다. 본 논문은 학습모델 설계에사용 가능한 2가지 loss 함수와 8가지 label 기법을 설명하고, 비프로파일링 분석과 소비전력모델 관점에서 각 label기법의 분석성능을 예측했다. 해밍웨이트 소비전력모델을 가정했을 때의 비프로파일링 분석 특징을 고려해서 One-hot인코딩을 적용하지 않은 HW(Hamming Weight) label과 CO(Correlation Optimization) loss를 적용한 학습모델이 가장 좋은 분석성능을 가질 것으로 예측했다. 그리고 AES-128 1라운드 Subbytes 연산 부분 데이터 집합 3가지에 대해 실제 분석을 수행했다. 제시한 각 label 기법과 loss 함수를 적용한 총 16가지 MLP(Multi-Layer Perceptron)기반 학습모델로 두 데이터 집합을 비프로파일링 분석하여 예측에 대해 검증했다.
Abstract
Recently, a deep learning-based non-profiling side-channel analysis was proposed. The deep learning-based non-profiling analysis is a technique that trains a neural network model for all guessed keys and then finds the correct secret key through the difference in the training metrics. As the performance of non-profiling analysis varies greatly depending on the neural network training model design, a correct model design criterion is required. This paper describes the two types of loss functions and eight labeling methods used in the training model design. It predicts the analysis performance of each labeling method in terms of non-profiling analysis and power consumption model. Considering the characteristics of non-profiling analysis and the HW (Hamming Weight) power consumption model is assumed, we predict that the learning model applying the HW label without One-hot encoding and the Correlation Optimization (CO) loss will have the best analysis performance. And we performed actual analysis on three data sets that are Subbytes operation part of AES-128 1 round. We verified our prediction by non-profiling analyzing two data sets with a total 16 of MLP-based model, which we describe.
참고문헌 (14)
- S. Chari, "Template attacks", LNCS, 2523, pp.13~28 (2003)
- P. Kocher, "Differential power analysis", LNCS, 1666, pp.388~397 (1999)
- 진성현, "Recent advances in deep learning‐based side‐channel analysis", ETRI Journal, 42(2), pp.292~304 (2020), 한국전자통신연구원[DOI]
- B. Hettwer, "Applications of machine learning techniques in side-channel attacks: a survey", Journal of Cryptographic Engineering, 10(2), pp.135~162 (2019)
- Z. Martinasek, "Profiling power analysis attack based on mlp in DPA contest v4.2", Telecommunications and Signal Processing, pp.223~226 (2016)
- E. Cagli, "Convolutional neural networks with data augmentation against jitter-based countermeasures", Cryptographic Hardware and Embedded Systems, CHES 2017, pp.45~68 (2017)
- I. Oh, "Machine Learning" (2017), Hanbit Academy
- B. Timon, "Non-profiled deep learning-based side-channel attacks with sensitivity analysis", IACR Transactions on Cryptographic Hardware and Embedded Systems, TCHES, pp.107~131 (2019)
- J. Park, "Non-profiled side channel attack based on deep learning using picture trace", ePrint, ~ (2019)
- P. Robyns, "Improving CEMA using correlation optimization", IACR Transactions on Cryptographic Hardware and Embedded Systems, TCHES (2018)
- "Inc,N.T.ChipWhisperer-Lite"[URL]
- "Inc, ETRI"[URL]
- R. Benadjila, "Deep learning for side-channel analysis and introduction to ASCAD database", Journal of Cryptographic Engineering, 10(2), pp.163~188 (2019)
- "ANSSI: Ascad database"[URL]