Interpreting Adversarial Examples with Attributes

17 Apr 2019  ·  Sadaf Gulshad, Jan Hendrik Metzen, Arnold Smeulders, Zeynep Akata ·

Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction... We propose to enable black-box neural networks to justify their reasoning both for clean and for adversarial examples by leveraging attributes, i.e. visually discriminative properties of objects. We rank attributes based on their class relevance, i.e. how the classification decision changes when the input is visually slightly perturbed, as well as image relevance, i.e. how well the attributes can be localized on both clean and perturbed images. We present comprehensive experiments for attribute prediction, adversarial example generation, adversarially robust learning, and their qualitative and quantitative analysis using predicted attributes on three benchmark datasets. read more

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here