Ikibazo gihuza ibibazo · Hagati Urwego

Ingero zo guhangana hamwe n'ikibazo gikomeye

Gerageza gusobanukirwa ingero zurwanya, ubumenyi bwibitero, icyitegererezo cyiterabwoba, kwirinda imyitozo, hamwe nisuzuma rikomeye.

Inzira zijyanye no kuyoboraIngero zo guhangana no gukomera
Ikibazo 1 Bya 8

Under a specified threat model, what is an adversarial example?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Under a specified threat model, what is an adversarial example?
    • An input crafted to cause a model error using changes allowed by that threat model
    • Any ordinary prediction error on unmodified input
    • An input that must contain tiny, imperceptible pixel changes
    • A model update that improves accuracy on every distribution
  2. Ni iki gitandukanya igitero 'cyera-agasanduku' n'igitero 'umukara-agasanduku'?
    • Agasanduku-cyera gatera gusa amashusho yera
    • Muri cyera-agasanduku, uwagabye igitero afite uburyo bwo kwerekana imiterere yimbere / gradients; mukirabura-agasanduku, gusa ibisubizo
    • Ibitero byirabura-byihuta buri gihe byihuse
    • Ibitero byera-bisanduku ntibisaba kubara
  3. FGSM (Uburyo bwihuta bwerekana ibimenyetso) ikora urugero rwo guhangana na ...
    • Guhinduranya pigiseli
    • Kongera imyitozo kuva kera
    • Gufata intambwe mucyerekezo cyikimenyetso cyigihombo gipimo cyerekeranye ninjiza
    • Gutema ishusho
  4. What is adversarial training commonly used for?
    • Guaranteeing robustness to every possible attack
    • Proving a classifier is fair
    • Eliminating all clean-data errors
    • Improving robustness against the adversarial threat model represented during training
  5. Ni ukubera iki 'kwimura' ingero zo guhangana zerekeye?
    • Igitero cyakozwe kuri moderi imwe gikunze kubeshya izindi moderi, bigatuma ibitero byirabura-agasanduku
    • Bituma moderi itoza buhoro
    • Yongera ikiguzi cyo kubika
    • Ihindura gusa amajwi yerekana amajwi
  6. How are prompt-injection attacks related to image adversarial examples?
    • They are identical bounded pixel perturbations
    • Both exploit model vulnerabilities, but prompt injection has a distinct instruction and system threat model
    • Prompt injection requires changing model weights
    • Image adversarial examples only affect text prompts
  7. Why must an adversarial-robustness report specify the perturbation norm and budget?
    • They determine the model’s number of parameters
    • They guarantee transfer to every attack
    • They define which input changes the reported robustness claim covers
    • They replace the need to state an attacker’s access
  8. Which pair of measures helps distinguish clean performance from performance under a specified attack?
    • Training-set size and GPU memory
    • Tokenization rate and context length
    • Model file size and parameter dtype
    • Clean accuracy and robust accuracy under the stated attack setting