arXiv Analytics

Sign in

arXiv:1809.08999 [cs.LG]AbstractReferencesReviewsResources

Fast Geometrically-Perturbed Adversarial Faces

Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi

Published 2018-09-24Version 1

The state-of-the-art performance of deep learning algorithms has led to a considerable increase in the utilization of machine learning in security-sensitive and critical applications. However, it has recently been shown that a small and carefully crafted perturbation in the input space can completely fool a deep model. In this study, we explore the extent to which face recognition systems are vulnerable to geometrically-perturbed adversarial faces. We propose a fast landmark manipulation method for generating adversarial faces, which is approximately 200 times faster than the previous geometric attacks and obtains 99.86% success rate on the state-of-the-art face recognition models. To further force the generated samples to be natural, we introduce a second attack constrained on the semantic structure of the face which has the half speed of the first attack with the success rate of 99.96%. Both attacks are extremely robust against the state-of-the-art defense methods with the success rate of equal or greater than 53.59%.

Related articles:
arXiv:1212.2415 [cs.LG] (Published 2012-12-11)
Robust Face Recognition using Local Illumination Normalization and Discriminant Feature Point Selection