Machine learningPrivacy-preserving analysis
差分隐私
差分隐私是一种数学框架，用于在提供严格保证个体记录无法被识别或推断的前提下，发布关于数据集的统计信息。该框架由 Cynthia Dwork 于 2006 年提出，它将隐私形式化为一个概率界限：任何单个个体在数据集中是否存在，最多只会将输出分布改变一个 e^ε 的乘法因子，其中 ε 是控制隐私-实用性权衡的隐私预算。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12. DOI: 10.1007/11787006_1 ↗
如何引用本页
ScholarGate. (2026, June 2). Differential Privacy. ScholarGate. https://scholargate.app/zh/privacy/differential-privacy
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →