Detecting Adversarial Examples through Nonlinear Dimensionality Reduction

Francesco Crecchi; Davide Bacciu; Battista Biggio

Detecting Adversarial Examples through Nonlinear Dimensionality Reduction

Machine Learning 2019-05-02 v2 Cryptography and Security Machine Learning

Authors: Francesco Crecchi , Davide Bacciu , Battista Biggio

Abstract

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density estimation techniques. Our empirical findings show that the proposed approach is able to effectively detect adversarial examples crafted by non-adaptive attackers, i.e., not specifically tuned to bypass the detection method. Given our promising results, we plan to extend our analysis to adaptive attackers in future work.

Keywords

adversarial examples adversarial attacks adversarial training

Cite

@article{arxiv.1904.13094,
  title  = {Detecting Adversarial Examples through Nonlinear Dimensionality Reduction},
  author = {Francesco Crecchi and Davide Bacciu and Battista Biggio},
  journal= {arXiv preprint arXiv:1904.13094},
  year   = {2019}
}

Comments

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2019

Detecting Adversarial Examples through Nonlinear Dimensionality Reduction

Abstract

Keywords

Cite

Comments

Related papers