Translated Title: 扩散去噪平滑，用于经认证和对抗性鲁棒的OOD检测 Translated Abstract: 随着机器学习的应用不断扩大，确保其安全性变得至关重要。在此方面的关键问题是能否识别给定样本是否来自训练分布，或者是一种“Out-Of-Distribution”（OOD）样本。此外，对手可以以使分类器做出自信预测的方式操作OOD样本。在本研究中，我们提出了一种新颖的方法，用于在$\ell_2$范围内认证OOD检测的鲁棒性，而不受网络体系结构或需要具体组件或额外培训的影响。此外，我们改进了当前用于检测OOD样本上的对抗性攻击的技术，同时在内部的样本上提供高水平的认证和对抗性鲁棒性。所有CIFAR10/100的OOD检测指标的平均值相对于以前的方法提高了约$\sim 13\%/5\%$。 (Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection)

翻译：Translated Title: 扩散去噪平滑，用于经认证和对抗性鲁棒的OOD检测 Translated Abstract: 随着机器学习的应用不断扩大，确保其安全性变得至关重要。在此方面的关键问题是能否识别给定样本是否来自训练分布，或者是一种“Out-Of-Distribution”（OOD）样本。此外，对手可以以使分类器做出自信预测的方式操作OOD样本。在本研究中，我们提出了一种新颖的方法，用于在$\ell_2$范围内认证OOD检测的鲁棒性，而不受网络体系结构或需要具体组件或额外培训的影响。此外，我们改进了当前用于检测OOD样本上的对抗性攻击的技术，同时在内部的样本上提供高水平的认证和对抗性鲁棒性。所有CIFAR10/100的OOD检测指标的平均值相对于以前的方法提高了约$\sim 13\%/5\%$。

Nicola Franco,Daniel Korth,Jeanette Miriam Lorenz,Karsten Roscher,Stephan Guennemann

As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an "Out-Of-Distribution" (OOD) sample. In addition, adversaries can manipulate OOD samples in ways that lead a classifier to make a confident prediction. In this study, we present a novel approach for certifying the robustness of OOD detection within a $\ell_2$-norm around the input, regardless of network architecture and without the need for specific components or additional training. Further, we improve current techniques for detecting adversarial attacks on OOD samples, while providing high levels of certified and adversarial robustness on in-distribution samples. The average of all OOD detection metrics on CIFAR10/100 shows an increase of $\sim 13 \% / 5\%$ relative to previous approaches.

翻译：