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 2407.02870cs.LGcs.AI
收藏

针对时间序列模型的成员推理攻击

Membership Inference Attacks Against Time-Series Models

IBM Research(IBM研究院)

Noam Koren, Abigail Goldsteen, Guy Amit, Ariel Farkash

AI总结:

本文研究了时间序列预测模型的成员推理攻击(MIA),通过引入基于多变量傅里叶变换的季节性特征和低阶多项式趋势分量,提升了攻击在识别成员身份上的有效性,从而更好地评估医疗数据的隐私风险。

摘要:

分析包含个人信息的时间序列数据,特别是在医疗领域,会引发严重的隐私担忧。来自患者的敏感健康数据通常被用于训练用于诊断和持续护理的机器学习模型。评估此类模型的隐私风险对于决定是否在生产环境中使用模型或将其与第三方共享至关重要。成员推理攻击(MIA)是此类评估的关键方法,然而时间序列预测模型在这一背景下尚未得到深入研究。我们探索了现有的MIA技术,并引入了新特征,重点关注数据的季节性和趋势分量。季节性使用多变量傅里叶变换进行估计,趋势则使用低阶多项式进行近似。我们将这些技术应用于各种类型的时间序列模型,使用了来自健康领域的数据集。结果表明,这些新特征增强了MIA在识别成员身份方面的有效性,提升了对医疗数据应用中隐私风险的理解。

英文摘要:

Analyzing time-series data that contains personal information, particularly in the medical field, presents serious privacy concerns. Sensitive health data from patients is often used to train machine learning models for diagnostics and ongoing care. Assessing the privacy risk of such models is crucial to making knowledgeable decisions on whether to use a model in production or share it with third parties. Membership Inference Attacks (MIA) are a key method for this kind of evaluation, however time-series prediction models have not been thoroughly studied in this context. We explore existing MIA techniques on time-series models, and introduce new features, focusing on the seasonality and trend components of the data. Seasonality is estimated using a multivariate Fourier transform, and a low-degree polynomial is used to approximate trends. We applied these techniques to various types of time-series models, using datasets from the health domain. Our results demonstrate that these new features enhance the effectiveness of MIAs in identifying membership, improving the understanding of privacy risks in medical data applications.

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。

↑