We introduce a simple, easy to implement, and computationally efficient tropical convolutional neural network architecture that is robust against adversarial attacks. We exploit the tropical nature of piece-wise linear neural networks by embedding the data in the tropical projective torus in a single hidden layer which can be added to any model. We study the geometry of its decision boundary theoretically and show its robustness against adversarial attacks on image datasets using computational experiments.

翻译：我们提出一种简单、易实现且计算高效的热带卷积神经网络架构，该架构对对抗攻击具有鲁棒性。通过将数据嵌入热带投影环面并在单一隐藏层中实现，我们能够充分利用分段线性神经网络的热带特性，且该隐藏层可附加至任意模型。我们从理论上研究了其决策边界的几何结构，并通过图像数据集的计算实验证明其对对抗攻击的鲁棒性。