강효주, 하재철, 홍성우, 이영주,

Vol. 34, No. 5, pp. 855-863, 10월. 2024
10.13089/JKIISC.2024.34.5.855, Full Text:
Keywords: Artificial Intelligent Security, deep neural network, Fault injection attack, Clock Glitch-based Fault Injection, Hardware Security
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.

Statistics
Cite this article