Peter Lorenz, Mario Fernandez, Jens Müller, Ullrich Köthe
TL;DR研究检测和防御方法，以保护深度学习模型免受不符合预期数据、对抗性示例和逃避攻击的影响。
Abstract
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in real-world scenarios. In recent years, many ood detectors have been developed, and even the benchmarking has bee