Adversarial Examples for Semantic Image Segmentation

Volker Fischer, Mummadi Chaithanya Kumar, Jan Hendrik Metzen, Thomas Brox

Abstract:

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic segmentation. We show how existing adversarial attackers can be transferred to this task and that it is possible to create imperceptible adversarial perturbations
that lead a deep network to misclassify almost all pixels of a chosen class while leaving network prediction nearly unchanged outside this class.

TL;DR: This work analyses the phenomenon of adversarial examples for the task of semantic image segmentation.

Keywords: Computer vision, Deep learning, Supervised Learning

Conflicts: bosch.com, uni-freiburg.de, dfki.de, uni-bremen.de