Informative Outlier Matters: Robustifying Out-of-distribution Detection Using Outlier Mining

Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha

Keywords: OOD detection, informative outlier mining, robustness

Abstract: Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types of adversarial OOD inputs. While methods leveraging auxiliary OOD data have emerged, our analysis reveals a key insight that the majority of auxiliary OOD examples may not meaningfully improve the decision boundary of the OOD detector. In this paper, we provide a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection. We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks. ATOM achieves state-of-the-art performance under a broad family of classic and adversarial OOD evaluation tasks. For example, on the CIFAR-10 in-distribution dataset, ATOM reduces the FPR95 by up to 57.99\% under adversarial OOD inputs, surpassing the previous best baseline by a large margin.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs and establishes state-of-the-art performance.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=CHSVNdfBS-