论文标题
可及的分类器和回归模型集：（非 - 鲁棒性分析和鲁棒训练
Reachable Sets of Classifiers and Regression Models: (Non-)Robustness Analysis and Robust Training
论文作者
论文摘要
神经网络在分类和回归任务方面具有出色的准确性。但是，理解他们的行为仍然是一个公开的挑战，需要关于预测的鲁棒性，解释性和可靠性来解决问题。我们通过计算可触及的神经网络的集合，即连续的输入集产生的输出集来回答这些问题。我们提供了两种有效的方法，可导致可触及套件的过度和不足。正如我们所展示的那样，该原理是高度用途的。首先，我们使用它来分析和增强分类器和回归模型的鲁棒性特性。这与现有作品相反，后者主要集中在分类上。具体而言，我们验证（非）鲁棒性，提出了一个健壮的训练程序，并表明我们的方法优于对抗性攻击，以及为非符号绑定扰动验证分类器的最新方法。其次，我们提供了区分未标记输入的可靠和不可靠预测的技术，以量化每个特征对预测的影响并计算特征排名。
Neural networks achieve outstanding accuracy in classification and regression tasks. However, understanding their behavior still remains an open challenge that requires questions to be addressed on the robustness, explainability and reliability of predictions. We answer these questions by computing reachable sets of neural networks, i.e. sets of outputs resulting from continuous sets of inputs. We provide two efficient approaches that lead to over- and under-approximations of the reachable set. This principle is highly versatile, as we show. First, we use it to analyze and enhance the robustness properties of both classifiers and regression models. This is in contrast to existing works, which are mainly focused on classification. Specifically, we verify (non-)robustness, propose a robust training procedure, and show that our approach outperforms adversarial attacks as well as state-of-the-art methods of verifying classifiers for non-norm bound perturbations. Second, we provide techniques to distinguish between reliable and non-reliable predictions for unlabeled inputs, to quantify the influence of each feature on a prediction, and compute a feature ranking.
