Detecting Adversarial Examples in Batches -- a geometrical approach. (arXiv:2206.08738v1 [cs.LG])

Web: http://arxiv.org/abs/2206.08738

Many deep learning methods have successfully solved complex tasks in computer
vision and speech recognition applications. Nonetheless, the robustness of
these models has been found to be vulnerable to perturbed inputs or adversarial
examples, which are imperceptible to the human eye, but lead the model to
erroneous output decisions. In this study, we adapt and introduce two geometric
metrics, density and coverage, and evaluate their use in detecting adversarial
samples in batches of unseen data. We empirically study these metrics …

arxiv examples lg