提出可高效评估神经网络对输入噪声鲁棒性的新方法。
Robustness of neural networks to random noise perturbations of their inputs
- 将网络视为黑箱，通过简单计算给出误差上界。
- 实验证明该方法在多个真实数据集上有效。
- 引入鲁棒性曲线，便于跨数据集对比分析。
我们研究了训练好的神经网络对其输入值扰动的鲁棒性问题。具体而言，考察了网络精度（以均方误差衡量）与鲁棒性之间的关系。为此，我们提出一种鲁棒性度量，该度量在高概率下为网络在给定输入扰动下的均方误差提供了上界。该度量计算简便且高效，无需网络内部结构信息，仅需将其视为黑箱。我们在多个真实数据集上进行了实验，验证了该方法的有效性。此外，我们还引入了鲁棒性曲线，使我们能够更深入地分析数据集内部及数据集之间的鲁棒性差异。
原文摘要 · Abstract (English)
We investigate the problem of the robustness of a trained neural network to the perturbation of its input values. More specifically, we examine the interplay between the accuracy of the network, as measured by the mean squared error, and robustness. Accordingly, we present a robustness measure, which, with high probability, suggests an upper bound on the mean squared error of the network, with respect to an input data set, for a given perturbation of the input values of the network. The measure we propose is both simple and efficient to compute, treating the neural network as a black box. We provide experimental results on several real-world data sets showing the efficacy of the proposed method. We also introduce the concept of robustness curves, which allows us to further analyse robustness within and between data sets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。