首页> 外文会议>Approximation, randomization, and combinatorial optimization : Algorithms and techniques >Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
【24h】

Private Learning and Sanitization: Pure vs. Approximate Differential Privacy

机译:私人学习和消毒:纯与近似差分隐私

获取原文
获取原文并翻译 | 示例

摘要

We compare the sample complexity of private learning and sanitization tasks under pure ε-differential privacy [Dwork, McSherry, Nissim, and Smith TCC 2006] and approximate (ε, δ)-differential privacy [Dwork, Kenthapadi, McSherry, Mironov, and Naor EUROCRYPT 2006]. We show that the sample complexity of these tasks under approximate differential privacy can be significantly lower than that under pure differential privacy.
机译:我们比较了纯ε差异隐私[Dwork,McSherry,Nissim和Smith Smith TCC 2006]和近似(ε,δ)差异隐私[Dwork,Kenthapadi,McSherry,Mironov和Naor的私人学习和消毒任务的样本复杂性EUROCRYPT 2006]。我们表明,在近似差异隐私下,这些任务的样本复杂度可以明显低于纯差异隐私下的任务。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号