AAISM AI Risk Management Practice Question
A model is vulnerable to 'Evasion Attacks' using FGSM (Fast Gradient Sign Method). Which architectural change most effectively increases robustness?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Applying Defensive Distillation.
FGSM uses the model's gradients to craft perturbations; defensive distillation or adversarial training helps mask these gradients.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increasing the learning rate during training.
Why it's wrong here
Learning rate changes do not improve robustness to evasion.
- ✗
Switching to a larger neural network.
Why it's wrong here
Larger networks can often be more vulnerable to adversarial examples.
- ✓
Applying Defensive Distillation.
Why this is correct
Defensive distillation makes the model less sensitive to small gradient changes.
- ✗
Implementing input denoising.
Why it's wrong here
Denoising helps with random noise but not deliberate gradient-based attacks.
About these practice questions
This AAISM question is part of Courseiva's 205-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed August 2026 · checked against the official ISACA exam blueprint
This AAISM practice question is part of Courseiva's free ISACA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AAISM exam.