Image adversarial attacks

Generate adversarial perturbations that cause vision models to misclassify - SimBA, NES, ZOO, HopSkipJump.

These attacks generate adversarial perturbations to images that cause vision models to misclassify. Import from dreadnode.airt.

SimBA (Simple Black-box Attack)

Iterative random perturbation. Adds small random changes to image pixels and keeps changes that move the model toward misclassification.

from dreadnode.airt import simba_attack

Black-box gradient estimation using natural evolution strategies. Estimates gradients without access to model internals.

from dreadnode.airt import nes_attack

Coordinate-wise gradient estimation. Approximates gradients one pixel at a time for targeted misclassification.

from dreadnode.airt import zoo_attack

Decision-based attack that only needs the model’s final prediction (not confidence scores). Works with the least model access.

from dreadnode.airt import hopskipjump_attack