arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.18671cs.CRcs.LG
收藏

针对聚合位置数据的零辅助知识成员推理攻击

A Zero Auxiliary Knowledge Membership Inference Attack on Aggregate Location Data

Imperial College London(伦敦帝国学院);EPFL(洛桑联邦理工学院)

Vincent Guan, Florent Guépin, Ana-Maria Cretu, Yves-Alexandre de Montjoye

AI总结:

针对聚合位置数据成员推理攻击需辅助数据集的不现实假设,本文提出首个零辅助知识MIA,通过从发布数据生成合成轨迹并纠正偏差,在多种隐私设置下匹配最先进攻击效果,凸显了强DP保护的必要性。

摘要:

位置数据通常从人群中收集,并以聚合形式共享以指导政策和决策制定。然而,聚合数据的普及也引发了成员推理攻击(MIAs)的隐私担忧。MIAs用于推断某个个体的数据是否参与了聚合发布。尽管目前已开发出针对聚合位置数据的有效MIA,但这些方法需要访问在相同位置收集的、来自相似人群的广泛个体轨迹辅助数据集。鉴于位置数据常见的隐私保护实践,这一假设往往是不切实际的。为了衡量现实对手执行MIA的风险,我们开发了首个针对聚合位置数据的零辅助知识(ZK)MIA,消除了对真实个体轨迹辅助数据集的需求。相反,我们开发了一种新颖的合成方法,从而从发布的聚合数据中生成合适的合成轨迹。我们还开发了纠正偏差和噪声的方法,以表明在发布前应用隐私机制时,我们基于合成数据的攻击仍然适用。使用两个大规模位置数据集,我们证明了我们的ZK MIA在广泛的设置下与最先进的Knock-Knock(KK)MIA相匹配,包括差分隐私(DP)的流行实现和小计数的抑制。此外,我们表明,即使对手仅知道其目标位置历史的一小部分(10%),ZK MIA仍然非常有效。这表明现实对手可以执行有效的MIA,凸显了强DP保护的必要性。

英文摘要:

Location data is frequently collected from populations and shared in aggregate form to guide policy and decision making. However, the prevalence of aggregated data also raises the privacy concern of membership inference attacks (MIAs). MIAs infer whether an individual's data contributed to the aggregate release. Although effective MIAs have been developed for aggregate location data, these require access to an extensive auxiliary dataset of individual traces over the same locations, which are collected from a similar population. This assumption is often impractical given common privacy practices surrounding location data. To measure the risk of an MIA performed by a realistic adversary, we develop the first Zero Auxiliary Knowledge (ZK) MIA on aggregate location data, which eliminates the need for an auxiliary dataset of real individual traces. Instead, we develop a novel synthetic approach, such that suitable synthetic traces are generated from the released aggregate. We also develop methods to correct for bias and noise, to show that our synthetic-based attack is still applicable when privacy mechanisms are applied prior to release. Using two large-scale location datasets, we demonstrate that our ZK MIA matches the state-of-the-art Knock-Knock (KK) MIA across a wide range of settings, including popular implementations of differential privacy (DP) and suppression of small counts. Furthermore, we show that ZK MIA remains highly effective even when the adversary only knows a small fraction (10%) of their target's location history. This demonstrates that effective MIAs can be performed by realistic adversaries, highlighting the need for strong DP protection.

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。

↑