引导式测验 · 硬 等级

差异隐私测验

练习差异隐私敏感性、组合和 DP-SGD，包括为什么正式的隐私损失界限与不记忆的承诺不同。

相关引导路径差异隐私
问题 1 的 8

For otherwise comparable differential-privacy mechanisms, what does a smaller epsilon specify?

预览每个问题8 问题

当您参加测验时，就会出现答案和解释。

  1. For otherwise comparable differential-privacy mechanisms, what does a smaller epsilon specify?
    • A larger dataset file
    • An increased model parameter count
    • A tighter bound on the allowed privacy loss
    • A faster GPU clock
  2. Why is noise calibrated to sensitivity in a differential-privacy mechanism?
    • To encrypt every raw record
    • To limit how a permitted neighboring-data change affects released output distributions
    • To remove the need to define neighboring datasets
    • To guarantee every person is impossible to identify under all conditions
  3. 差异隐私的“本地”模型与“中央”模型有何区别？
    • 本地需要一个完全值得信赖的中央策展人
    • Local 根本不使用任何噪音
    • 本地仅适用于图像
    • 本地在数据离开之前在每个人的设备上添加噪音
  4. 校准噪声时“灵敏度”有何用途？
    • 衡量一个人的数据可以在多大程度上改变查询结果
    • 计算表中的列数
    • 检测硬件温度
    • 选择报告的字体
  5. 为什么每个新查询都要花费“隐私预算”？
    • 每行查询花费金钱
    • 隐私损失通过多次分析累积
    • 数据集随着每次查询而缩小
    • 预算仅与存储限制有关
  6. What does correctly configured DP-SGD aim to bound through clipping, noise, and privacy accounting?
    • Every possibility of memorizing any fact
    • The total number of model layers automatically
    • The need for a training objective
    • The privacy loss associated with the specified neighboring training datasets
  7. A count query includes each person at most once. Under adding or removing one person, what is its sensitivity?
    • 一
    • The entire number of database columns
    • Zero because it is a count
    • The model’s hidden dimension
  8. Two separately randomized analyses use the same private dataset. Why evaluate them together?
    • The second analysis deletes the first output
    • Each analysis makes the previous privacy cost exactly zero
    • Privacy loss can compose across the released outputs
    • Composition applies only to public data