Skip to content
AI Security

Interview question · Adversarial ML & Model Privacy

Explain FGSM and PGD, and what the perturbation budget means.

The two attacks every robustness paper starts from. The scored answer explains the gradient step, the budget as a threat model, and why the iterative attack is the standard for evaluation.

mediumNewPreparation tags: Google DeepMind, Meta, NVIDIAUpdated Nov 2026

The two attacks every robustness paper starts from. The scored answer explains the gradient step, the budget as a threat model, and why the iterative attack is the standard for evaluation.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 6 follow-ups like an interviewer would

An interviewer asks you to explain FGSM and PGD attacks on image classifiers and why PGD is the usual baseline for evaluating defences.

  1. What does FGSM do?
  2. How does PGD improve on it?
  3. What is epsilon, and why does it matter?
  4. What if a defence resists FGSM but not PGD?
  5. What if PGD fails but a black-box attack succeeds?
  6. How would you summarise FGSM and PGD for a defence evaluation?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackHow does adversarial training work, and what are its limits?Next in this trackWhat is gradient masking, and why is it a trap when you evaluate defences?Next in this trackA team claims their model is now robust to adversarial inputs. How do you evaluate that claim honestly?
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.