Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding

Utku Ozbulak, Arnout Van Messem, Wesley De Neve. Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding. In International Joint Conference on Neural Networks, IJCNN 2019 Budapest, Hungary, July 14-19, 2019. pages 1-8, IEEE, 2019. [doi]

Authors

Utku Ozbulak

This author has not been identified. Look up 'Utku Ozbulak' in Google

Arnout Van Messem

This author has not been identified. Look up 'Arnout Van Messem' in Google

Wesley De Neve

This author has not been identified. Look up 'Wesley De Neve' in Google