Articles, Blog

Neural Structured Learning – Part 4: Adversarial learning for image classification

February 14, 2020


3 Comments

  • Reply Niko Pumo-ri February 12, 2020 at 2:59 am

    apart from correctly classifying of the adversarial neighbors, is there any advantage of the model trained this way? Is there any influence on test accuracy, for example?

  • Reply Aristotelis Charalampakis February 12, 2020 at 10:41 pm

    perturbation based on reverse gradients… of what?

  • Reply Joseph Edappully February 13, 2020 at 10:18 am

    Does the "robustness" provided by this method mostly just increase robustness against adversarial examples generated in the same manner as this model, or is it more general/broad robustness? In other words, let's say another new method to generate adversarial examples is discovered/used, will this method be robust against that new method as well (without having knowledge/training of what the new method is)?

  • Leave a Reply