Idanwo ti o sopọ mọ itọsọna · Lile Ipele

Iyatọ Asiri adanwo

Practice differential privacy sensitivity, composition, and DP-SGD, including why formal privacy-loss bounds differ from promises of no memorization.

Jẹmọ itọsọna awọn ọnaIyatọ Asiri
Ibeere 1 ti 8

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

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  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. Kini o ṣe iyatọ awoṣe 'agbegbe' ti asiri iyatọ si awoṣe 'aarin'?
    • Agbegbe nilo olutọju aarin ti o ni igbẹkẹle ni kikun
    • Agbegbe ko lo ariwo rara rara
    • Agbegbe ṣiṣẹ nikan lori awọn aworan
    • Agbegbe ṣe afikun ariwo lori ẹrọ eniyan kọọkan ṣaaju ki data to lọ
  4. Kini 'ifamọ' ti a lo fun nigba mimu ariwo?
    • Didiwọn iye data eniyan kan le yi abajade ibeere kan pada
    • Kika awọn nọmba ti awọn ọwọn ni a tabili
    • Wiwa iwọn otutu hardware
    • Yiyan fonti kan fun ijabọ naa
  5. Kini idi ti ibeere tuntun kọọkan n na lati 'isuna-isuna ikọkọ'?
    • Awọn ibeere na owo fun kana
    • Pipadanu asiri kojọpọ kọja awọn itupalẹ lọpọlọpọ
    • Iṣeto data n dinku pẹlu ibeere kọọkan
    • Awọn inawo jẹ nipa awọn opin ibi ipamọ nikan
  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?
    • Ọkan
    • 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