论文标题
原子：使用离群挖掘的鲁棒性检测
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
论文作者
论文摘要
检测分布（OOD）输入对于在开放世界中安全部署深度学习模型至关重要。但是，在开放世界中，现有的OOD检测解决方案可能会脆弱，面临各种类型的对抗性OOD输入。尽管已经出现了利用辅助OOD数据的方法，但我们对发光示例的分析表明，一个关键的见解，即大多数辅助OOD示例可能不会有意义地改善甚至损害OOD检测器的决策边界，这在实际数据的经验结果中也可以观察到。在本文中，我们提供了一种理论上动机的方法，具有信息性离群挖掘（ATOM）（ATOM）的对抗训练，从而提高了OOD检测的稳健性。我们表明，通过挖掘信息丰富的辅助OOD数据，人们可以显着改善OOD检测性能，并且有些令人惊讶地概括了看不见的对抗性攻击。原子在广泛的经典和对抗性OOD评估任务下实现最先进的表现。例如，在CIFAR-10分布数据集上，原子将FPR（TPR 95％）降低了57.99％，在对抗性OOD输入下，将以前的最佳基线超过了一个最佳基线。
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 on illuminative examples reveals a key insight that the majority of auxiliary OOD examples may not meaningfully improve or even hurt the decision boundary of the OOD detector, which is also observed in empirical results on real data. 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 FPR (at TPR 95%) by up to 57.99% under adversarial OOD inputs, surpassing the previous best baseline by a large margin.
