MITIGATING ADVERSARIAL EFFECTS IN MACHINE LEARNING SYSTEMS

Techniques for sanitization of machine learning (ML) models are provided. A first ML model is received, along with clean training data. A path is trained between the first ML model and a second ML model using the clean training data. A sanitized ML model is generated based on at least one point on the trained path. One or more ML functionalities are then facilitated using the sanitized ML model.