Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems. (arXiv:2205.02604v1 [cs.CV])

Web: http://arxiv.org/abs/2205.02604

Adversarial attack perturbs an image with an imperceptible noise, leading to
incorrect model prediction. Recently, a few works showed inherent bias
associated with such attack (robustness bias), where certain subgroups in a
dataset (e.g. based on class, gender, etc.) are less robust than others. This
bias not only persists even after adversarial training, but often results in
severe performance discrepancies across these subgroups. Existing works
characterize the subgroup's robustness bias by only checking individual
sample's proximity to the decision boundary. …

arxiv building cv systems vulnerability