Adversarial Examples and Robustness Quiz

Answers and explanations appear as you take the quiz.

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. What distinguishes a 'white-box' attack from a 'black-box' attack?
   • White-box attacks only work on white images
   • In white-box, the attacker has access to the model's internals/gradients; in black-box, only outputs
   • Black-box attacks are always faster
   • White-box attacks require no computation
3. FGSM (Fast Gradient Sign Method) crafts an adversarial example by...
   • Randomly shuffling pixels
   • Retraining the model from scratch
   • Taking a step in the direction of the sign of the loss gradient with respect to the input
   • Cropping the image
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. Why is the 'transferability' of adversarial examples concerning?
   • An attack crafted on one model often fools other models, enabling black-box attacks
   • It makes models train slower
   • It increases storage costs
   • It only affects audio models
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