arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09575cs.LG
收藏

鲁棒模型的平稳点损失

Stationary Point Losses for Robust Model

Harbin Institute of Technology(哈尔滨工业大学);Saint-Petersburg State University(圣彼得堡国立大学)

Weiwei Gao, Dazhi Zhang, Yao Li, Zhichang Guo, Ovanes Petrosian

摘要:

无法保证鲁棒性是深度学习模型在安全要求高的领域应用的主要障碍之一。我们发现,最常用的交叉熵(CE)损失并不能保证神经网络的鲁棒边界。CE损失在决策边界处锐化神经网络以实现较低的损失,而不是将边界推到更鲁棒的位置。鲁棒的边界应该保持在来自不同类别的样本的中间,从而最大化从边界到样本的余量。我们认为这是由于CE损失没有固定点的缘故。在本文中,我们提出了一个家庭的新的损失,称为驻点(SP)损失,其中至少有一个驻点的正确分类侧。我们证明了鲁棒边界可以保证SP损失,而不会损失太多的精度。在SP损失的情况下,需要更大的扰动来生成对抗性示例。我们证明了鲁棒性提高各种对抗攻击下,通过应用SP损失。此外,通过SP损失学习的鲁棒边界在不平衡数据集上也表现良好。

英文摘要:

The inability to guarantee robustness is one of the major obstacles to the application of deep learning models in security-demanding domains. We identify that the most commonly used cross-entropy (CE) loss does not guarantee robust boundary for neural networks. CE loss sharpens the neural network at the decision boundary to achieve a lower loss, rather than pushing the boundary to a more robust position. A robust boundary should be kept in the middle of samples from different classes, thus maximizing the margins from the boundary to the samples. We think this is due to the fact that CE loss has no stationary point. In this paper, we propose a family of new losses, called stationary point (SP) loss, which has at least one stationary point on the correct classification side. We proved that robust boundary can be guaranteed by SP loss without losing much accuracy. With SP loss, larger perturbations are required to generate adversarial examples. We demonstrate that robustness is improved under a variety of adversarial attacks by applying SP loss. Moreover, robust boundary learned by SP loss also performs well on imbalanced datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑