VERIFYING REMOTE EXECUTION OF MACHINE LEARNING INFERENCE UNDER HOMOMORPHIC ENCRYPTION USING PERMUTATIONS

• Main Authors: Kushnir, Eyal, Soceanu, Omri, Masalha, Ramy, Drucker, Nir
• Format: Patent
• Language: English
• Published: 18.07.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

A technique to remotely identify potential compromise of a service provider that performs homomorphic inferencing on a model. For a set of real data samples on which the inferencing is to take place, at least first and second permutations of a set of trigger samples are generated. Every set of samples (both trigger and real samples) are then sent for homomorphic inferencing on the model at least twice, and in a secret permutated way. To improve performance, a permutation is packaged with the real data samples prior to encryption using a general purpose data structure, a tile tensor, that allows users to store multi-dimensional arrays (tensors) of arbitrary shapes and sizes. In response to receiving one or more results from the HE-based model inferencing, a determination is made whether the service provider is compromised. Upon a determination that the service provider is compromised, a given mitigation action is taken.