quiz bu lëkkale ak tegtal · Dëgër Niveau

Quiz bu wuute ci wàllu nëbbëtu

Jëfandikool sensitivite bu wuute ci wàllu nëbbëtu, composition, ak DP-SGD, boole ci li waral àppu ñàkka am àpp bu formeel wuute ak dige yu amul benn memori.

Yooni njiit yu jëm ciNjaboot gu wuute
Laaj 1 de 8

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

Xoolaatal laaj bu nekk8 laaj

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

  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. Lan moo wuutale xeetu 'local' bu wuute ci wàllu nëbbëtu ak xeetu 'central'?
    • Local mingi soxla kuratër bu mag buñu mëna wóolu
    • Local du musa jëfandikoo benn bruit
    • Local dafay liggéey ci nataal yi kese
    • Local dafay yokk bruit ci aparey ku nekk balaa done yi di dem
  4. Luy 'sensitivite' ngir kalibre bruit bi?
    • Natt ba ñaata done yu benn nit mëna soppi ci njariñu benn laaj
    • Lim limu kolon yi ci biir benn tablo
    • Gis tàngooru aparey bi
    • Tann ab font ngir rapoor bi
  5. Lan moo waral laaj bu bees bu nekk di dugal xaalis ci 'budget privacy'?
    • Laajte yi dañuy njëg xaalis ci liiñ bu nekk
    • Ñàkka am kàddu yu nëbbu dafay gëna yokk ci jàngat yu bari
    • Done yi dañuy wàññeeku ak laaj bu nekk
    • Budget yi dañuy wax ci wàllu dencukaay
  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?
    • Benn
    • 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