arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00138cs.LGcs.NEstat.ML
收藏

对抗性机器学习下的漏洞:偏差还是方差?

Vulnerability Under Adversarial Machine Learning: Bias or Variance?

Waterloo AI Institute, University of Waterloo(滑铁卢大学滑铁卢人工智能研究所);ADC Automotive Distance Control Systems GmbH, Continental(大陆集团ADC汽车距离控制系统有限公司)

Hossein Aboutalebi, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong

摘要:

先前的研究已经揭示了深度神经网络在对抗性机器学习背景下的脆弱性,导致最近对这一领域的极大关注。一个有趣的问题是对抗性机器学习的偏差-方差关系,这可能会为这种行为提供更深入的见解。偏差和方差的概念是分析和评价机器学习模型泛化能力和可靠性的主要方法之一。虽然它已被广泛用于其他机器学习模型,但在深度学习领域还没有得到很好的探索,在对抗性机器学习领域更是探索得很少。在这项研究中,我们研究了对抗性机器学习对训练的深度神经网络的偏差和方差的影响,并分析了对抗性扰动如何影响网络的泛化。我们推导出基于两个主要损失函数的分类和回归应用的偏差-方差权衡:(i)均方误差(MSE),和(ii)交叉熵。此外,我们进行定量分析与模拟和真实的数据,经验性地评估一致性与推导出的偏差方差权衡。我们的分析揭示了为什么深度神经网络从偏差-方差的角度来看在对抗性扰动下表现不佳,以及这种类型的扰动将如何改变网络的性能。此外,鉴于这些新的理论发现,我们引入了一种新的对抗性机器学习算法,其计算复杂性度低于众所周知的对抗性机器学习策略(例如,PGD),同时在较低的扰动幅度下欺骗深度神经网络时提供高成功率。

英文摘要:

Prior studies have unveiled the vulnerability of the deep neural networks in the context of adversarial machine learning, leading to great recent attention into this area. One interesting question that has yet to be fully explored is the bias-variance relationship of adversarial machine learning, which can potentially provide deeper insights into this behaviour. The notion of bias and variance is one of the main approaches to analyze and evaluate the generalization and reliability of a machine learning model. Although it has been extensively used in other machine learning models, it is not well explored in the field of deep learning and it is even less explored in the area of adversarial machine learning. In this study, we investigate the effect of adversarial machine learning on the bias and variance of a trained deep neural network and analyze how adversarial perturbations can affect the generalization of a network. We derive the bias-variance trade-off for both classification and regression applications based on two main loss functions: (i) mean squared error (MSE), and (ii) cross-entropy. Furthermore, we perform quantitative analysis with both simulated and real data to empirically evaluate consistency with the derived bias-variance tradeoffs. Our analysis sheds light on why the deep neural networks have poor performance under adversarial perturbation from a bias-variance point of view and how this type of perturbation would change the performance of a network. Moreover, given these new theoretical findings, we introduce a new adversarial machine learning algorithm with lower computational complexity than well-known adversarial machine learning strategies (e.g., PGD) while providing a high success rate in fooling deep neural networks in lower perturbation magnitudes.

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。

↑