Adversarial Robustness
Perturbation attacks, adversarial training, certified defences, and the robustness-accuracy tradeoff.
5concepts
58flashcards
36minutes of reading
- 01 Adversarial Examples and the Threat Model Why an imperceptible perturbation flips a confident classifier, what a norm ball is actually assuming, and why stating the threat model precisely is the first substantive step in any robustness claim.
- 02 Adversarial Training and Certified Defences The min-max formulation behind the only empirical defence that has held up, what a certificate actually guarantees, and the gap between certified and empirical robustness.
- 03 Data Poisoning and Backdoors How an attacker who controls a small fraction of training data can install a trigger, why backdoors are nearly invisible to standard evaluation, and what the web-scale training setting makes possible.
- 04 Model Extraction and Membership Inference What an attacker can learn from query access alone, why confident outputs leak training set membership, and the defences that trade utility for protection.
- 05 Robustness Evaluation That Means Something Why fixed-attack benchmarks systematically overstate robustness, what an adaptive evaluation requires, and the reporting practices that make a robustness claim checkable.