引導式測驗 · 中等 等級

會員推論攻擊測驗

研究訓練成員推理,包括影子模型、LiRA 校準、差分隱私邊界、誤報和攻擊評估。

相關引導路徑成員資格推斷攻擊
問題 1 的 8

成員推理攻擊試圖確定什麼?

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。

  1. 成員推理攻擊試圖確定什麼?
    • 特定記錄是否是訓練集的一部分
    • 模型的準確性
    • 模型的架構
    • 測試集的大小
  2. 过度拟合如何影响研究模型中的隶属推理暴露?
    • It proves every training record is identifiable with certainty
    • It removes the need to evaluate attack errors
    • It can increase the behavioral difference between members and comparable nonmembers
    • It makes all outputs independent of training data
  3. 2017 年 Shokri 等人最初採用了什麼技術?攻擊靠什麼?
    • 漸層裁切
    • 影子模型
    • 集束搜尋
    • 代幣化
  4. 為什麼即使不洩漏記錄內容,成員資格推斷也會有害?
    • 它會減慢模型速度
    • 它改變了模型的權重
    • 它刪除訓練數據
    • 會員資格本身可以揭露敏感事實,例如診斷
  5. 什么校准可以将所引用的 LiRA 方法与单一的朴素损失阈值区分开来?
    • A guarantee that every record has the same inherent difficulty
    • Only an increased generation temperature
    • Per-example score distributions estimated from in and out models
    • A requirement that the target reveal its entire training dataset
  6. What does a properly specified differential-privacy guarantee bound?
    • Changes in output probabilities between neighboring datasets
    • A guarantee that no attack can ever make any correct guess
    • A mandatory deletion of all model outputs
    • Only the raw number of files in a training folder
  7. An attack incorrectly flags 10 of 1,000 actual nonmembers as members. What is its false-positive rate on those nonmembers?
    • 10%
    • 0.1%
    • 100%
    • 1%
  8. Why does the LiRA paper emphasize true-positive rate at low false-positive rates?
    • False positives are impossible by definition
    • Average accuracy can conceal whether confidently flagged records are reliable membership evidence
    • Every member and nonmember population must have identical sizes
    • The model’s training accuracy directly gives attack precision