In recent years, a concept known as the vulnerability of machine-learning-based models has been presented, which shows that almost all learning models, including parametric and non-parametric models, are vulnerable. The most well- known of these vulnerabilities, or in other words, attacks, is injection of adversarial examples into the learning model, which is based on artificial neural networks, deep artificial neural networks specifically, have the highest degree of vulnerability to adversarial examples. The adversarial examples are such that they add noise to the input data of the target network’s neural network, so that the input data from the user’s eye will not change significantly, but it will make network, D_FY W_6D6F" Adversarial Examples, Gaussian Process, Neural Networks, Deep Learning, Probabilistic Model
