论文标题
确定性高斯平均神经网络
Deterministic Gaussian Averaged Neural Networks
论文作者
论文摘要
我们提出了一种确定性方法，用于计算回归和分类中使用的神经网络的高斯平均水平。我们的方法基于特定正规损失的训练与高斯平均值的预期值之间的等效性。我们使用这种等效性来证明在干净的数据上表现良好但对对抗性扰动不健壮的模型。就认证的准确性和对抗性鲁棒性而言，我们的方法与已知的随机方法（例如随机平滑）相媲美，但在推理过程中仅需要单个模型评估。
We present a deterministic method to compute the Gaussian average of neural networks used in regression and classification. Our method is based on an equivalence between training with a particular regularized loss, and the expected values of Gaussian averages. We use this equivalence to certify models which perform well on clean data but are not robust to adversarial perturbations. In terms of certified accuracy and adversarial robustness, our method is comparable to known stochastic methods such as randomized smoothing, but requires only a single model evaluation during inference.
