Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?

Authors: Anna-Kathrin Kopetzki, Bertrand Charpentier, Daniel Zügner, Sandhya Giri, Stephan Günnemann
Published: 2020-10-28 | Updated: 2021-06-11

Source: https://arxiv.org/abs/2010.14986

PDF: https://arxiv.org/pdf/2010.14986

Labels Predicted by AI

評価手法 生成モデルの課題 敵対的サンプル

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Dirichlet-based uncertainty (DBU) models are a recent and promising class of uncertainty-aware models. DBU models predict the parameters of a Dirichlet distribution to provide fast, high-quality uncertainty estimates alongside with class predictions. In this work, we present the first large-scale, in-depth study of the robustness of DBU models under adversarial attacks. Our results suggest that uncertainty estimates of DBU models are not robust w.r.t. three important tasks: (1) indicating correctly and wrongly classified samples; (2) detecting adversarial examples; and (3) distinguishing between in-distribution (ID) and out-of-distribution (OOD) data. Additionally, we explore the first approaches to make DBU models more robust. While adversarial training has a minor effect, our median smoothing based approach significantly increases robustness of DBU models.