Adversarial Phenomenon in the Eyes of Bayesian Deep Learning

• Main Authors: Rawat, Ambrish, Wistuba, Martin, Nicolae, Maria-Irina
• Format: Journal Article
• Language: English
• Published: 22-11-2017
• Subjects: Computer Science - Learning; Statistics - Machine Learning
• DOI: 10.48550/arxiv.1711.08244

Deep Learning models are vulnerable to adversarial examples, i.e.\ images
obtained via deliberate imperceptible perturbations, such that the model
misclassifies them with high confidence. However, class confidence by itself is
an incomplete picture of uncertainty. We therefore use principled Bayesian
methods to capture model uncertainty in prediction for observing adversarial
misclassification. We provide an extensive study with different Bayesian neural
networks attacked in both white-box and black-box setups. The behaviour of the
networks for noise, attacks and clean test data is compared. We observe that
Bayesian neural networks are uncertain in their predictions for adversarial
perturbations, a behaviour similar to the one observed for random Gaussian
perturbations. Thus, we conclude that Bayesian neural networks can be
considered for detecting adversarial examples.