论文标题
过度参数改善了针对对抗性攻击的鲁棒性：复制研究
Overparametrization improves robustness against adversarial attacks: A replication study
论文作者
论文摘要
过度透明化已成为机器学习的事实上的标准。尽管做出了许多努力，但我们对如何和何处的理解有助于建模准确性和鲁棒性。为此，我们在这里进行了一项实证研究，以系统地研究和复制该领域的先前发现，尤其是Madry等人的研究。与这项研究一起，我们的发现支持Bubeck等人最近提出的“鲁棒性的普遍定律”。我们认为，尽管对于强大的感知至关重要，但过多散文可能不足以实现完全的鲁棒性和更智能的体系结构，例如人类视觉皮层实施的那些似乎是不可避免的。
Overparametrization has become a de facto standard in machine learning. Despite numerous efforts, our understanding of how and where overparametrization helps model accuracy and robustness is still limited. To this end, here we conduct an empirical investigation to systemically study and replicate previous findings in this area, in particular the study by Madry et al. Together with this study, our findings support the "universal law of robustness" recently proposed by Bubeck et al. We argue that while critical for robust perception, overparametrization may not be enough to achieve full robustness and smarter architectures e.g. the ones implemented by the human visual cortex) seem inevitable.
