Detecting adversarial examples through nonlinear dimensionality reduction

Francesco Crecchi, Davide Bacciu, Battista Biggio

The European Symposium on Artificial Neural Networks · 2019 · 12 citations · 0 references

Concepts

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.