Adversarial Examples
-
How Adversarial Examples Fool Image Classifiers
Adversarial examples follow the model's own gradient: a 0.007 per-pixel nudge made GoogLeNet call a panda a gibbon at 99.3%. How and why it works.
-
How FGSM Adversarial Attacks Work: Fast Gradient Sign Method
FGSM adds one signed gradient step to every pixel to flip a classifier's prediction. The update rule, epsilon trade-offs, and why PGD replaced it.
-
Adversarial Attack Libraries: ART, Foolbox, torchattacks
ART, Foolbox, torchattacks, CleverHans and TextAttack compared on scope, framework support, attack coverage, licence and repository maintenance.
-
Adversarial Examples vs. Data Poisoning
Adversarial examples attack a deployed model at inference; data poisoning attacks the model before it is deployed. Different timing, different defenses.
-
Adversarial Patch Attacks in the Physical World
Printable adversarial patches use transformation-aware optimization to fool vision models across camera conditions and challenge current defenses.
-
Universal Adversarial Perturbations: One Vector, Many Inputs
Universal adversarial perturbations are input-agnostic: one crafted noise vector causes misclassification across most inputs and transfers between models.
-
Evasion Attacks on Image Classifiers: FGSM, PGD, and C&W
A technical comparison of FGSM, PGD, and C&W explains their optimization goals, threat models, benchmark roles, limitations, and defensive implications.
-
Adversarial Transferability: How Black-Box Attacks Work
Adversarial examples transfer across models with different architectures and training sets. Why that happens, and what it means for black-box defenses.