Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the network while preserving its accuracy. Several recent studies have addressed the relationship between model compression and adversarial robustness, while some experiments have reported contradictory results. This work summarizes available evidence and discusses possible explanations for the observed effects.

翻译：增加模型容量是提升深度学习网络对抗鲁棒性的已知方法。另一方面，包括剪枝和量化在内的多种模型压缩技术，可以在保持精度的同时减小网络规模。近期多项研究探讨了模型压缩与对抗鲁棒性之间的关系，但部分实验报告了相互矛盾的结果。本文总结了现有证据，并讨论了观察到的效应可能的解释。