Now showing items 1-1 of 1

    • Defense-GAN for text: protecting text classifiers against Adversarial Attacks 

      Ibáñez López, Bruno (Universitat Politècnica de Catalunya, 2019-06-18)
      Bachelor thesis
      Restricted access - author's decision
      In computer vision, Defense-GAN is a framework that leverages the capability of generative models to defend neural networks (NNs) against adversarial attacks. This paper investigates how Defense-GAN will behave when it is ...