ATTACK-DETERRENT GENERATOR, METHOD FOR PREVENTING AN ATTACK ON AN AI UNIT AND COMPUTER-READABLE STORAGE MEDIUM

Adversarial attacks pose a threat to the functioning of AI systems. A defense generator for dynamically generating at least one AI defense module is provided. A core feature of the invention is that a distribution function is determined for model data. The invention is based on the assumption that the model data belong to a model manifold, or have a similar statistical behavior. Thus, it is possible to determine for an input data set whether the data of the input data set can be associated with an adversarial attack. This is the case, for example, if statistical anomalies are found in the input data set.