arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.10567cs.LGstat.ML
收藏

数据增强如何影响机器学习中的隐私?

How Does Data Augmentation Affect Privacy in Machine Learning?

Microsoft Research Asia(微软亚洲研究院)

Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu

摘要:

据观察,在文献中,数据增强可以显着减轻隶属推理(MI)攻击。然而,在这项工作中,我们通过提出新的MI攻击来利用增强数据的信息来挑战这一观察结果。MI攻击被广泛用于度量模型对训练集的信息泄漏。我们建立了最优隶属度推断模型训练时,增广数据,这启发我们制定MI攻击作为一个集合分类问题,即,对一组增强实例而不是单个数据点进行分类,并设计输入置换不变特征。从经验上讲,我们证明了所提出的方法普遍优于原始方法时,模型与数据增强训练。更进一步,我们表明,所提出的方法可以实现更高的MI攻击的成功率与一些数据增强训练模型比现有的方法没有数据增强训练模型。值得注意的是,我们在CIFAR10上实现了70.1%的MI攻击成功率,而以前的最佳方法仅达到61.9%。这表明,使用数据增强训练的模型的隐私风险可能在很大程度上被低估了。

英文摘要:

It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposing new MI attacks to utilize the information of augmented data. MI attack is widely used to measure the model's information leakage of the training set. We establish the optimal membership inference when the model is trained with augmented data, which inspires us to formulate the MI attack as a set classification problem, i.e., classifying a set of augmented instances instead of a single data point, and design input permutation invariant features. Empirically, we demonstrate that the proposed approach universally outperforms original methods when the model is trained with data augmentation. Even further, we show that the proposed approach can achieve higher MI attack success rates on models trained with some data augmentation than the existing methods on models trained without data augmentation. Notably, we achieve a 70.1% MI attack success rate on CIFAR10 against a wide residual network while the previous best approach only attains 61.9%. This suggests the privacy risk of models trained with data augmentation could be largely underestimated.

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。

↑