ADVERSARIAL SAMPLE PROTECTION FOR MACHINE LEARNING

• Main Authors: KELLERMANN, Raizy, NAYSHTUT, Alex, LEVY, Dor, BEN-SHALOM, Omer
• Format: Patent
• Language: English; French; German
• Published: 28.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

Adversarial sample protection for machine learning is described. An example of a storage medium includes instructions for initiating processing of examples for training of an inference engine in a system; dynamically selecting a subset of defensive preprocessing methods from a repository of defensive preprocessing methods for a current iteration of processing, wherein a subset of defensive preprocessing methods is selected for each iteration of processing; performing training of the inference engine with a plurality of examples, wherein the training of the inference engine include operation of the selected subset of defensive preprocessing methods; and performing an inference operation with the inference engine, including utilizing the selected subset of preprocessing defenses for the current iteration of processing.