[2A6-GS-2] Machine learning

[2A6-GS-2-01] On the Defense Method for Adversarial Examples Patch Attack against Object Detection

〇Yoshihiro Koseki¹ (1. Mitsubishi Electric Corporation)

Keywords:Adversarial Examples

In this work, we propose a defense method to disable the effect of adversarial examples patch attack against object detection by painting bounding boxes which have a score value lower than detection threshold. We show our method is effective by evaluation over INRIA Person Dataset.