An Empirical Look at Gradient-based Black-box Adversarial Attacks on Deep Neural Networks Using One-point Residual Estimates

In recent years, there has been a great deal of studies about the optimisation of generating adversarial examples for Deep Neural Networks (DNNs) in a black-box environment. The use of gradient-based techniques to get the adversarial images in a minimal amount of input-output correspondence with the attacked model has been extensively studied....