Create a custom practice set
Pick category, difficulty, number of questions, and time limit. Start instantly with your own quiz.
Generate QuizGK Question
Which technique protects ML models from adversarial attacks by training with perturbed inputs?
- Adversarial Training
- Defensive Distillation
- Both A and B
- Neither
Answer: Both A and B
Adversarial training includes adversarial examples in training data; defensive distillation smooths model outputs. Both improve robustness against adversarial attacks.