11
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Ensemble Noise Simulation to Handle Uncertainty about Gradient-based Adversarial Attacks

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Gradient-based adversarial attacks on neural networks can be crafted in a variety of ways by varying either how the attack algorithm relies on the gradient, the network architecture used for crafting the attack, or both. Most recent work has focused on defending classifiers in a case where there is no uncertainty about the attacker's behavior (i.e., the attacker is expected to generate a specific attack using a specific network architecture). However, if the attacker is not guaranteed to behave in a certain way, the literature lacks methods in devising a strategic defense. We fill this gap by simulating the attacker's noisy perturbation using a variety of attack algorithms based on gradients of various classifiers. We perform our analysis using a pre-processing Denoising Autoencoder (DAE) defense that is trained with the simulated noise. We demonstrate significant improvements in post-attack accuracy, using our proposed ensemble-trained defense, compared to a situation where no effort is made to handle uncertainty.

          Related collections

          Author and article information

          Journal
          26 January 2020
          Article
          2001.09486
          70ce9e2a-c77a-4935-acf5-8321c0df42a1

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          6 pages, 4 figures
          cs.LG cs.CR stat.ML

          Security & Cryptology,Machine learning,Artificial intelligence
          Security & Cryptology, Machine learning, Artificial intelligence

          Comments

          Comment on this article