misaali noon ak laaj ak tontu

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

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. Lan mooy wuutale songu 'kees bu weex' ak songu 'kees bu ñuul'?
   • White-box attack yi ci nataal yu weex yi kese lañuy dox
   • Ci white-box, ki koy song mën na dugg ci biir model bi/gradient yi; ci black-box, génne yi kese
   • Cong black-box mooy gëna gaaw saa yu nekk
   • Cong mu boyet bu weex soxlawul xayma
3. FGSM (Méthode de signe gradient rapide) defar na misaalu noon ci...
   • pixel yu ñuy jaxase ci anam wu mucc
   • Taggaat model bi ci noonu
   • Jéego ci wàllu màndarga gradient perte ci wàllu dugal
   • Dagg nataal bi
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. Lan moo waral 'mën toxal' misaali noon yi?
   • Cong buñ defaree ci benn model dafay faral di nax yeneen model, loolu mooy tax ñu mëna def cong mu black-box
   • Dafay tax model yi di gëna yeex
   • Dafay yokk njëgu dencukaay bi
   • Du am njeexital ci model audio yi
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