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 2605.14686cs.LG
收藏

ReMIA:一种强大的、高效的对抗合成数据生成器成员推断攻击的替代方案

ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators

Aindo SpA(Aindo公司)

Davide Scassola, Andrea Coser, Sebastiano Saccani

AI总结:

ReMIA是一种高效的隐私度量方法,通过生成两个合成数据集并测量分类器能否识别记录来源,相比传统方法更实用且敏感度相当。

摘要:

在隐私约束下共享表格数据对研究和协作越来越重要。合成数据生成器(SDGs)是可行的解决方案,但合成数据仍易受攻击,如成员推断攻击(MIAs),旨在确定特定记录是否属于训练数据。最先进的MIAs强大但不实用:它们依赖于影子建模,需要数百次SDG训练运行,并需要辅助数据,其规模是原始训练集的几倍。快速代理指标如最接近记录的距离(DCR)效率高但对MIAs风险的敏感性有限。我们介绍了ReMIA(相对成员推断攻击),一种实用的隐私度量方法,仅需两次SDG训练运行和不超过原始训练集大小的附加数据。与预测记录是否在训练集中不同,ReMIA从两个源数据集生成两个合成数据集,并测量分类器能否识别记录来源。在多个表格数据集和SDGs上的实验表明,ReMIA的敏感度与最先进的MIAs相当,但实用性显著更高。我们进一步观察到SDGs可以实现传统噪声基匿名化方法无法达到的隐私-效用权衡。代码可在https://github.com/aindo-com/remia获取。

英文摘要:

Tabular data sharing under privacy constraints is increasingly important for research and collaboration. Synthetic data generators (SDGs) are a promising solution, but synthetic data remains vulnerable to attacks, such as membership inference attacks (MIAs), which aim to determine whether a specific record was part of the training data. State-of-the-art MIAs are powerful but impractical: they rely on shadow modeling, requiring hundreds of SDG training runs, and need auxiliary data several times larger than the original training set. Fast proxy metrics like distance to closest record (DCR) are efficient but have limited sensitivity to MIA risk. We introduce ReMIA (Relative Membership Inference Attack), a practical privacy metric that requires only two SDG training runs and additional data no larger than the original training set. Rather than predicting whether a record was in the training set, ReMIA generates two synthetic datasets from two source datasets and measures whether a classifier can identify which source a record came from. Experiments across multiple tabular datasets and SDGs show that ReMIA has a sensitivity comparable to state-of-the-art MIAs while being substantially more practical. We further observe that SDGs can achieve privacy-utility trade-offs that traditional noise-based anonymization methods do not match. Code is available at https://github.com/aindo-com/remia.

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。

↑