encode the [0, 1] interval constraint. Friendly to many off-the-shelf optimizers, e.g. Adam. • To optimize logits Skip sigmoid() to avoid vanishing gradient. Carlini, Nicholas, and David Wagner. “Towards Evaluating the Robustness of Neural Networks.” IEEE S&P (Oakland) 2016.
with the total variation regularization. • [Distortions] Color management with the non-printability loss. • [Inaccurate Patch] Random transformation during optimization iterations. • …… Sharif, Mahmood, et al. "Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition." ACM CCS 2016.