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。
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。
- 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
- 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
- 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
- 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
- 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
- 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
- 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%
- 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