Quiz

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy attack inference membre bi di jéema xam?
   • Ndax benn dokimaa bokk na ci liñ tàggat
   • njubteg model bi
   • architecture model bi
   • Dayo ensemble test bi
2. How can overfitting affect membership-inference exposure in studied models?
   • 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. Ban pexe lañu def ci 2017 Shokri et al. attack
   • Dagg degrade
   • Modèlu lëndëm
   • Seetug limyéer
   • Tokenisasioŋ
4. Lan moo waral inference membership mën na jur loraange doonte kenn xamul limu ëmb ci dosiye bi?
   • Dafay yeexal model bi
   • Dafay soppi diisaayu model bi
   • Dafay efaase done yiñ tàggat
   • Ndaw ci boppam mën na fësal mbir yu am solo, lu melni diagnostic
5. What calibration distinguishes the cited LiRA approach from a single naive loss threshold?
   • 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