arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.06372cs.LGcs.CV
收藏

非鲁棒特征在单类分类中并非始终有用

Non-Robust Features are Not Always Useful in One-Class Classification

Georgia Tech(佐治亚理工学院);Technology Innovation Institute(技术创新研究院)

Matthew Lau, Haoran Wang, Alec Helbling, Matthew Hul, ShengYun Peng, Martin Andreoni, Willian T. Lunardi, Wenke Lee

AI总结:

该研究针对单类分类实际应用中轻量级模型的对抗样本威胁展开,发现轻量级单类分类器在强攻击下学习的非鲁棒特征并非始终对任务有用,这类特征是训练的不良副产品。

摘要:

对抗样本的存在使得机器学习模型的鲁棒性受到质疑。本文研究了需使用轻量级模型的单类分类实际应用中对抗样本带来的威胁。基于Ilyas等人(2019)的研究,我们探究了轻量级单类分类器对对抗攻击的脆弱性及其可能原因。结果表明,在更强攻击下,轻量级单类分类器学习到的是不具备鲁棒性的特征(例如纹理)。但与多类分类中的情况(Ilyas等人,2019)不同,这些非鲁棒特征对单类任务并非始终有用,这说明学习这些无预测性的非鲁棒特征是训练过程产生的不良结果。

英文摘要:

The robustness of machine learning models has been questioned by the existence of adversarial examples. We examine the threat of adversarial examples in practical applications that require lightweight models for one-class classification. Building on Ilyas et al. (2019), we investigate the vulnerability of lightweight one-class classifiers to adversarial attacks and possible reasons for it. Our results show that lightweight one-class classifiers learn features that are not robust (e.g. texture) under stronger attacks. However, unlike in multi-class classification (Ilyas et al., 2019), these non-robust features are not always useful for the one-class task, suggesting that learning these unpredictive and non-robust features is an unwanted consequence of training.

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。

↑