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 2302.05545cs.CRcs.ITcs.LGmath.IT
收藏

在垂直联邦学习中对抗无差别的推理攻击

Privacy Against Agnostic Inference Attacks in Vertical Federated Learning

School of Computer Science and Electronic Engineering, University of Essex(埃塞克斯大学计算机科学与电子工程学院)

Morteza Varasteh

AI总结:

研究提出垂直联邦学习中一种新的推理攻击形式,通过在训练阶段获取独立训练的机器学习模型,主动方可对训练和预测样本进行推理攻击,提出隐私保护方案以平衡被动方隐私与主动方可解释性。

摘要:

本文提出了一种垂直联邦学习(VFL)中新的推理攻击形式,其中两个方合作训练机器学习(ML)模型。考虑逻辑回归作为VFL模型。一个方(称为主动方)拥有训练阶段样本的真实标签,而另一个方(称为被动方)仅分享对应样本的独立特征集。研究表明,主动方可通过独立训练的ML模型对训练和预测阶段的样本进行推理攻击。这种攻击不需要主动方知晓特定样本的分数,因此称为无差别推理攻击。研究表明,利用预测阶段观察到的置信度分数可提高主动方自主ML模型的性能,从而提升无差别推理攻击的质量。作为对策,提出隐私保护方案(PPSs)。虽然所提方案保持了VFL模型的效用,但系统性地扭曲了与被动方特征相关的VFL参数。对被动方参数施加的扭曲程度可调,从而在隐私保护与主动方可解释性之间产生权衡。被动方参数的扭曲程度可根据双方的隐私和可解释性需求进行选择,以期使双方(部分)满意。最后,实验结果展示了所提攻击和PPSs的有效性。

英文摘要:

A novel form of inference attack in vertical federated learning (VFL) is proposed, where two parties collaborate in training a machine learning (ML) model. Logistic regression is considered for the VFL model. One party, referred to as the active party, possesses the ground truth labels of the samples in the training phase, while the other, referred to as the passive party, only shares a separate set of features corresponding to these samples. It is shown that the active party can carry out inference attacks on both training and prediction phase samples by acquiring an ML model independently trained on the training samples available to them. This type of inference attack does not require the active party to be aware of the score of a specific sample, hence it is referred to as an agnostic inference attack. It is shown that utilizing the observed confidence scores during the prediction phase, before the time of the attack, can improve the performance of the active party's autonomous ML model, and thus improve the quality of the agnostic inference attack. As a countermeasure, privacy-preserving schemes (PPSs) are proposed. While the proposed schemes preserve the utility of the VFL model, they systematically distort the VFL parameters corresponding to the passive party's features. The level of the distortion imposed on the passive party's parameters is adjustable, giving rise to a trade-off between privacy of the passive party and interpretabiliy of the VFL outcomes by the active party. The distortion level of the passive party's parameters could be chosen carefully according to the privacy and interpretabiliy concerns of the passive and active parties, respectively, with the hope of keeping both parties (partially) satisfied. Finally, experimental results demonstrate the effectiveness of the proposed attack and the PPSs.

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。

↑