부채널 분석을 이용한 딥러닝 네트워크 신규 내부 비밀정보 복원 방법 연구
Reverse Engineering of Deep Learning Network Secret Information Through Side Channel Attack
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
IoT 장비의 발달로 딥러닝 가속기의 필요성이 증대됨에 따라 이에 탑재되는 딥러닝 가속기의 구현 및 안전성 검증에 대한 연구가 활발히 진행 중이다. 본 논문에서는 Usenix 2019에 발표된 딥러닝 네트워크 복원 논문의 한계점을 극복한 내부 비밀정보 신규 부채널 분석 방법론에 대해 제안한다. 기존 연구에서 네트워크 내부 가중치의 범위를 제한하며 32비트 가중치의 16비트만 복원한 단점이 있다, 제안하는 신규 가중치 복원 방법으로 상관전력분석을 이용하여 IEEE754 32비트 단정밀도 가중치를 99% 정확도로 복원할 수 있음을 보인다. 또한 특정 입력값에 대해서만 활성함수 복원이 가능한 기존 연구의 제약을 극복하고, 딥러닝을 이용한 신규 활성함수 복원 방법으로 입력값에 대한 조건 없이 99% 정확도로 활성함수를 복원한다. 이를 통해 기존 연구가 가지는 한계점들을 극복했을 뿐만 아니라 제안하는 신규 방법론이 효과적이라는 것을 입증한다.
Abstract
As the need for a deep learning accelerator increases with the development of IoT equipment, research on the implementation and safety verification of the deep learning accelerator is actively. In this paper, we propose a new side channel analysis methodology for secret information that overcomes the limitations of the previous study in Usenix 2019. We overcome the disadvantage of limiting the range of weights and restoring only a portion of the weights in the previous work, and restore the IEEE754 32bit single-precision with 99% accuracy with a new method using CPA. In addition, it overcomes the limitations of existing studies that can reverse activation functions only for specific inputs. Using deep learning, we reverse activation functions with 99% accuracy without conditions for input values with a new method. This paper not only overcomes the limitations of previous studies, but also proves that the proposed new methodology is effective.
참고문헌 (19)
- Y. LeCun, "Deep learning", Nature, 521, pp.436~444 (2015)
- I. J. Goodfellow, "Explaining and Harnessing Adversarial Examples", International Conference on Learning Representations (2015)
- S. Mangard, "Power Analysis Attacks: Revealing the Secrets of Smart Cards", pp.101~118 (2008)
- P. Kocher, "Differential power analysis, in Advances in Cryptology, CRYPTO’ 99", LNCS, 1666, pp.388~397 (1999)
- E. Brier, "Correlation power analysis with a leakage model, in Cryptographic Hardware and Embedded Systems", LNCS, 3156, pp.16~29 (2004)
- H. Maghrebi, "Breaking cryptographic implementations using deep learning techniques, in International Conference on Security, Privacy, and Applied Cryptography Engineering", LNCS, 10076, pp.3~26 (2016)
- E. Cagli, "Convolutional neural networks with data augmentation against jitter-based countermeasures, in International Conference on Cryptographic Hardware and Embedded Systems", LNCS, 10529, pp.45~68 (2017)
- L. Batina, "CSI NN : Reverse engineering of neural network architectures through electromagnetic side channel", Proceedings of the 28th USENIX Conference on Security Symposium, pp.515~532 (2019)
- H. Yu, "DeepEM: Deep Neural Networks Model Recovery through EM Side-Channel Information Leakage", Proceedings of the 2020 IEEE International Symposium on Hardware Oriented Security and Trust, pp.209~218 (2020)
- K. Yoshida, "Model Reverse-Engineering Attack using Correlation Power Analysis against Systolic Array Based Neural Network Accelerator", Proceedings of the 2020 IEEE International Symposium on Circuits and Systems, pp.1~5 (2020)
- K. Yoshida, "Model Reverse-Engineering Attack against Systolic-Array-Based DNN Accelerator Using Correlation Power Analysis", IEICE Trans. Fundam. Electron. Commun. Computer Science, pp.152~161 (2021)
- S. Maji, "Leaky Nets:Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels–Attacks and Defenses", IEEE Internet Things Journal, pp.12079~12092 (2021)
- G. Takatoi, "Simple Electromagnetic Analysis Against Activation Functions of Deep Neural Networks, in Applied Cryptography and Network Security Workshops", LNCS, 12418, pp.181~197 (2020)
- X. Hu, "DeepSniffer : A DNN Model Extraction Framework Based on Learning Architectural Hints", Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, pp.385~399 (2020)
- Francois-Xavier Standaert, "Secure integrated circuits and systems", pp.27~42 (2010)
- M. MéndezReal, "Physical Side–Channel Attacks on Embedded Neural Networks : A Survey", Applied Sciences, pp.6790~ (2021)
- 진성현, "Recent advances in deep learning‐based side‐channel analysis", ETRI Journal, 42(2), pp.292~304 (2020), 한국전자통신연구원[DOI]
- F. Zhang, "Persistent fault analysis on block ciphers", IACR Transactions on Cryptographic Hardware and Embedded Systems, pp.150~172 (2018)
- W. Hua, "Reverse engineering convolutional neural networks through side-channel information leaks", Proceedings of the 55th Annual Design Automation Conference, pp.1~6 (2018)