Detecting Adversarial Examples through Nonlinear Dimensionality Reduction [article]

Francesco Crecchi, Davide Bacciu, Battista Biggio
2019 arXiv   pre-print
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.
arXiv:1904.13094v2 fatcat:hd7bpc6fxzfjpan24f5nh2537q