论文标题
重新思考鲁棒性聚类
Rethinking Clustering for Robustness
论文作者
论文摘要
本文研究了深度神经网络训练中令人鼓舞的语义对齐特征如何增加网络鲁棒性。最近的著作观察到，对抗训练会导致强大的模型，其学识渊博的特征似乎与人类的感知相关。受到从鲁棒性到语义的联系的启发，我们研究了互补连接：从语义到鲁棒性。为此，我们为基于距离的分类模型（基于聚类的分类器）提供了鲁棒性证书。此外，我们表明该证书很紧张，我们利用它提出了clustrust（稳健性的聚类培训），这是一个基于聚类和对手的培训框架，以学习健壮的模型。有趣的是，在强PGD攻击下，\ textit {clustr}的表现优于对手训练的网络，最高为$ 4 \％$。
This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to correlate with human perception. Inspired by this connection from robustness to semantics, we study the complementary connection: from semantics to robustness. To do so, we provide a robustness certificate for distance-based classification models (clustering-based classifiers). Moreover, we show that this certificate is tight, and we leverage it to propose ClusTR (Clustering Training for Robustness), a clustering-based and adversary-free training framework to learn robust models. Interestingly, \textit{ClusTR} outperforms adversarially-trained networks by up to $4\%$ under strong PGD attacks.
