Abstract: The invariant ellipsoid method is aimed at minimization of the smallest invariant and attractive set of a control system operating under bounded external disturbances and parametric ...
Abstract: Adversarial attacks craft adversarial examples (AEs) to fool convolution neural networks. The mainstream gradient-based attacks, based on first-order optimization methods, encounter ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results