Detecting Black-box Adversarial Examples through Nonlinear Dimensionality Reduction

Francesco Crecchi, Davide Bacciu, Battista Biggio
2019 The European Symposium on Artificial Neural Networks  
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
more » ... end our analysis to adaptive attackers in future work.
dblp:conf/esann/CrecchiBB19 fatcat:vvzw2avibrcnvh2pemcsrzhqhe