Accepted paper @ ESANN19: Detecting Black-box Adversarial Examples through Nonlinear Dimensionality Reduction


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 dimensional- ity 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.

Bruges (Belgium)
Francesco Crecchi
Ph.D. Student in Adversarial Machine Learning