Deep Neural Network에 대한 클럭 글리치 기반 오류 주입 공격
Clock Glitch-based Fault Injection Attack on Deep Neural Network
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
심층 신경망(DNN, Deep Neural Network)은 데이터 분석 및 예측에 있어서 높은 효율성으로 인하여 점점 다양한 분야에서 활용되고 있다. 그러나 심층 신경망의 사용이 빈번해짐에 따라, 이와 관련된 보안 위협 요소도 증가하고 있다. 특히, 심층 신경망의 예측에 직접적인 영향을 미칠 수 있는 순전파(forward propagation) 과정과 활성화 함수(activation function)에서 오류가 발생하면, 모델의 예측 정확도에 치명적인 영향을 미칠 수 있다. 본 논문에서는 심층 신경망에서 입력층을 제외한 각 계층으로의 순전파 과정과 출력층에서 사용되는 Softmax 함수에 오류 주입 공격을 수행하고, 그 실험 결과를 분석하였다. MNIST 데이터셋에 대해 글리치 클럭을 이용한 오류 주입 결과, 반복문에 오류를 주입하면 시스템 파라미터에 따른 결정론적 오분류가 일어남을 확인하였다.
Abstract
The use of Deep Neural Network (DNN) is gradually increasing in various fields due to their high efficiency in data analysis and prediction. However, as the use of deep neural networks becomes more frequent, the security threats associated with them are also increasing. In particular, if a fault occurs in the forward propagation process and activation function that can directly affect the prediction of deep neural network, it can have a fatal damage on the prediction accuracy of the model. In this paper, we performed some fault injection attacks on the forward propagation process of each layer except the input layer in a deep neural network and the Softmax function used in the output layer, and analyzed the experimental results. As a result of fault injection on the MNIST dataset using a glitch clock, we confirmed that faut injection on into the iteration statements can conduct deterministic misclassification depending on the network parameters.
참고문헌 (8)
- Y. Liu, "Fault injection attack on deep neural network", IEEE, 2017, 131~138
- S. Tajik, "Security and Artificial Intelligence:A Crossdisciplinary Approach", pp.72~84 (2022)
- Y. LeCun, "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86(22), pp.2278~2324 (1998)
- J. Breier, "SNIFF: reverse engineering of neural networks with fault attacks", IEEE Transactions on Reliability, 71(4), pp.1527~1539 (2021)
- X. Hou, "Physical security of deep learning on edge devices : Comprehensive evaluation of fault injection attack vectors", Microelectronics Reliability, 120, pp.114116~ (2021)
- Y. Fukuda, "Fault injection attacks utilizing waveform pattern matching against neural networks processing on microcontroller", IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 105(3), pp.300~310 (2022)
- W. Liu, "Imperceptible misclassification attack on deep learning accelerator by glitch injection", 2020 57th ACM, 2020, 1~6
- J. Breier, "Practical fault attack on deep neural networks", Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, pp.2204~2206 (2018)