Recent work has shown the defense of 01 loss sign activation neural networks against image classification adversarial attacks. A public challenge to attack the models on CIFAR10 dataset remains undefeated. We ask the following question in this study: are 01 loss sign activation neural networks hard to deceive with a popular black box text adversarial attack program called TextFooler? We study this question on four popular text classification datasets: IMDB reviews, Yelp reviews, MR sentiment classification, and AG news classification. We find that our 01 loss sign activation network is much harder to attack with TextFooler compared to sigmoid activation cross entropy and binary neural networks. We also study a 01 loss sign activation convolutional neural network with a novel global pooling step specific to sign activation networks. With this new variation we see a significant gain in adversarial accuracy rendering TextFooler practically useless against it. We make our code freely available at \url{https://github.com/zero-one-loss/wordcnn01} and \url{https://github.com/xyzacademic/mlp01example}. Our work here suggests that 01 loss sign activation networks could be further developed to create fool proof models against text adversarial attacks.

翻译：近期研究表明，零一损失符号激活神经网络在图像分类对抗攻击中展现出防御能力。针对CIFAR10数据集上攻击此类模型的公开挑战至今未被攻克。本研究提出以下问题：使用名为TextFooler的流行黑盒文本对抗攻击程序，零一损失符号激活神经网络是否难以被欺骗？我们在四个主流文本分类数据集上研究了该问题：IMDB评论、Yelp评论、MR情感分类及AG新闻分类。研究发现，相较于Sigmoid激活的交叉熵网络与二值神经网络，零一损失符号激活网络更难被TextFooler攻击成功。我们还提出了一种结合新型全局池化层的零一损失符号激活卷积神经网络，该池化层专为符号激活网络设计。通过这一变体，对抗准确性显著提升，使TextFooler几乎失效。我们的代码已开源发布于 \url{https://github.com/zero-one-loss/wordcnn01} 和 \url{https://github.com/xyzacademic/mlp01example}。本研究结果表明，零一损失符号激活网络可进一步发展为针对文本对抗攻击的防欺骗模型。