arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.05034cs.CR
收藏

GCON:基于目标扰动的差分隐私图卷积网络

GCON: Differentially Private Graph Convolutional Network via Objective Perturbation

Jianxin Wei, Yizheng Zhu, Xiaokui Xiao, Ergute Bao, Yin Yang, Kuntai Cai, Beng Chin Ooi

AI总结:

针对图卷积网络在差分隐私下训练导致消息聚合失真和效用降低的问题,提出GCON,通过目标函数扰动保持图卷积过程不变,提供紧致敏感度界限,在边差分隐私下实现更优模型效用。

摘要:

图卷积网络(GCN)是一种流行的机器学习模型,在图分析中有广泛应用,包括医疗、交通和金融。然而,在没有隐私保护措施下训练的GCN可能会通过其模型参数记住训练数据中的私人人际关系。这构成了通过链接攻击破坏隐私的重大风险,可能导致违反GDPR等隐私法规。为了防御此类攻击,一种有前景的方法是使用差分隐私(DP)训练GCN,这是一种通过在训练过程中注入随机噪声来提供强隐私保护的严格框架。然而,在DP下训练GCN是一项极具挑战性的任务。现有解决方案要么扰动图拓扑,要么在图卷积操作中注入随机性,要么高估所需的噪声量,导致网络消息聚合严重失真,从而降低模型效用。受此启发,我们提出了GCON,一种新颖且有效的边差分隐私GCN训练解决方案。GCON利用扰动目标函数以满足DP的经典思想,并保持图卷积过程不变。我们严格的理论分析给出了图卷积结果敏感度的紧致闭式界限,并量化了边修改对训练模型参数的影响。在多种设置下使用多个基准数据集进行的大量实验证明了GCON相对于现有解决方案的一致优越性。

英文摘要:

Graph Convolutional Networks (GCNs) are a popular machine learning model with a wide range of applications in graph analytics, including healthcare, transportation, and finance. However, a GCN trained without privacy protection measures may memorize private interpersonal relationships in the training data through its model parameters. This poses a substantial risk of compromising privacy through link attacks, potentially leading to violations of privacy regulations such as GDPR. To defend against such attacks, a promising approach is to train the GCN with differential privacy (DP), a rigorous framework that provides strong privacy protection by injecting random noise into the training process. However, training a GCN under DP is a highly challenging task. Existing solutions either perturb the graph topology or inject randomness into the graph convolution operations, or overestimate the amount of noise required, resulting in severe distortions of the network's message aggregation and, thus, poor model utility. Motivated by this, we propose GCON, a novel and effective solution for training GCNs with edge differential privacy. GCON leverages the classic idea of perturbing the objective function to satisfy DP and maintains an unaltered graph convolution process. Our rigorous theoretical analysis offers tight, closed-form bounds on the sensitivity of the graph convolution results and quantifies the impact of an edge modification on the trained model parameters. Extensive experiments using multiple benchmark datasets across diverse settings demonstrate the consistent superiority of GCON over existing solutions.

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。

↑