Fault injection attacks on SoftMax function in deep neural networks
Dirmanto Jap, Yoo-Seung Won, Shivam Bhasin · 2021
Softmax is commonly used activation function in neural networks to normalize the output to probability distribution over predicted classes. Being often deployed in the output layer, it can potentially be targeted by fault injection attacks to create misclassification. In this extended abstract, we perform a preliminary fault analysis of Softmax against single bit faults.