Guide-yakabatana mibvunzo · Zvakaoma Nhanho

Differential Privacy Quiz

Dzidzira kusiyanisa kuvanzika senitivity, kuumbwa, uye DP-SGD, kusanganisira nei zviri pamutemo kuvanzika-kurasikirwa miganhu yakasiyana nezvipikirwa zvekusaziva nemusoro.

Nzira dzekutungamira dzinoenderanaKusiyanisa Kuvanzika
Mubvunzo 1 ye 8

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

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  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. Chii chinosiyanisa modhi ye'nzvimbo' yekusiyanisa zvakavanzika kubva kune 'yepakati' modhi?
    • Local inoda muchengeti wepakati akavimbika
    • Local haamboshandisi chero ruzha zvachose
    • Local inoshanda pamifananidzo chete
    • Yemunharaunda inowedzera ruzha pachishandiso chemunhu wega data risati raenda
  4. Chii chinonzi 'sensitivity' chinoshandiswa pakugadzirisa ruzha?
    • Kuyera kuti ingani data remunhu mumwe chete rinogona kushandura mhinduro yemubvunzo
    • Kuverenga nhamba yemakoramu mutafura
    • Kuona tembiricha yehardware
    • Kusarudza font yemushumo
  5. Sei mubvunzo mutsva wega wega uchipedza kubva ku'mari yekuvanzika'?
    • Mibvunzo inoda mari pamutsara
    • Kurasikirwa kwekuvanzika kunounganidza pakuongorora kwakawanda
    • Iyo dataset inodzikira nemubvunzo wega wega
    • Mabhajeti ari pamusoro pemiganhu yekuchengetedza
  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?
    • Imwe
    • 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