Traditional ML attacks
Black-box attacks against ML classifiers - evasion, model extraction, membership inference, model inversion, and image adversarial attacks.
Beyond generative models, Dreadnode red-teams black-box ML classifiers (tabular, text, and image) through their prediction API. Import any of these from dreadnode.airt and point them at a classifier’s predict endpoint. See Traditional ML Red Teaming for the end-to-end workflow.
EvasionPerturb an input with query access only until the classifier misclassifies it.
Model extractionReconstruct a surrogate copy of the target model from its query responses.
Membership inferenceDetermine whether a specific record was in the target model's training set.
Model inversionReconstruct representative inputs for a target class from the model.
Image adversarialGenerate adversarial perturbations that cause vision models to misclassify.