引導式測驗 · 硬 等級
差異隱私測驗
練習差異隱私敏感度、組合和 DP-SGD,包括為什麼正式的隱私損失界線與不記憶的承諾不同。
問題 1 的 8
For otherwise comparable differential-privacy mechanisms, what does a smaller epsilon specify?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 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
- 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
- 差異隱私的「本地」模型與「中央」模型有何不同?
- 本地需要一個完全值得信賴的中央策展人
- Local 根本不使用任何噪音
- 本地僅適用於映像
- 本地在數據離開之前在每個人的設備上添加噪音
- 校準噪音時「靈敏度」有何用途?
- 衡量一個人的資料可以在多大程度上改變查詢結果
- 計算表中的列數
- 檢測硬體溫度
- 選擇報告的字體
- 為什麼每個新查詢都要花費「隱私預算」?
- 每行查詢花錢
- 隱私損失透過多次分析累積
- 資料集隨著每次查詢而縮小
- 預算僅與儲存限制有關
- 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
- 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
- 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