arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09478cs.CRcs.LG
收藏

数据重构攻击与防御:一项系统性评估

Data Reconstruction Attacks and Defenses: A Systematic Evaluation

Stanford University(斯坦福大学);New York University(纽约大学);Peking University(北京大学)

Sheng Liu, Zihan Wang, Yuxiao Chen, Qi Lei

AI总结:

该研究将机器学习数据重构攻击问题视为逆问题,推导了两层神经网络重构误差的算法上界与匹配的信息论下界,定义了效用-隐私权衡评估指标,并提出强重构攻击以更新对防御方法强度的认知。

摘要:

重构攻击与防御对于理解机器学习中的数据泄露问题至关重要。然而,现有研究主要围绕梯度反转攻击的实证观察展开,缺乏理论基础,且无法区分防御方法的实际效用与攻击方法的计算局限性。在本研究中,我们提出将该问题视为一个逆问题,从而能够从理论层面系统性地评估数据重构攻击。针对多种防御方法,我们推导了两层神经网络重构误差的算法上界,以及与之匹配的(在特征维度和架构维度上)信息论下界。为补充理论结果并探究效用-隐私权衡,我们定义了一种自然的防御方法评估指标,该指标在最强攻击下衡量相近效用损失的防御表现。我们进一步提出了一种强重构攻击,在我们提出的评估指标下,这一攻击有助于更新此前关于防御方法强度的部分认知。

英文摘要:

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and cannot disentangle the usefulness of defending methods from the computational limitation of attacking methods. In this work, we propose to view the problem as an inverse problem, enabling us to theoretically and systematically evaluate the data reconstruction attack. On various defense methods, we derived the algorithmic upper bound and the matching (in feature dimension and architecture dimension) information-theoretical lower bound on the reconstruction error for two-layer neural networks. To complement the theoretical results and investigate the utility-privacy trade-off, we defined a natural evaluation metric of the defense methods with similar utility loss among the strongest attacks. We further propose a strong reconstruction attack that helps update some previous understanding of the strength of defense methods under our proposed evaluation metric.

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。

↑