Despite the success of neural networks, the issue of classification robustness remains, particularly highlighted by adversarial examples. In this paper, we address this challenge by focusing on the continuum of functions implemented in artificial neurons, ranging from pure AND gates to pure OR gates. Our hypothesis is that the presence of a sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. These measures involve rescaling inputs to the [-1,1] interval and reducing the number of points in the steepest section of the sigmoidal activation function. A crucial component of our method is the comparison between a neuron's output distribution when fed with the actual dataset and a randomised version called the "scrambled dataset." Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.

翻译：尽管神经网络取得了成功，但分类鲁棒性问题仍然存在，对抗性样本尤其凸显了这一问题。本文通过聚焦人工神经元中实现的函数连续统（从纯与门到纯或门）来应对这一挑战。我们假设网络中若存在足够数量的类或神经元，可能导致分类脆弱性增加，进而更易受到对抗攻击。我们定义了类与神经元，并提出了提高其在网络中比例的措施：将输入重新缩放到[-1,1]区间，并减少Sigmoid型激活函数最陡峭区域的采样点数。该方法的关键在于比较神经元在真实数据集与称为"打乱数据集"的随机化版本上输出的分布差异。在MNIST数据集上的实验结果表明，我们的方法有望作为未来探索的可行方向。