Partition a Tensor with Varying Granularity Levels in Shuffled Secure Multiparty Computation: abstract simplified (17715877)

• This abstract for appeared for patent application number 17715877 Titled 'Partition a Tensor with Varying Granularity Levels in Shuffled Secure Multiparty Computation'

Simplified Explanation

The abstract discusses a method for protecting access to a tensor in outsourced deep learning computations. In this method, the tensor is divided into different portions of varying sizes. Computing tasks are then generated to operate on these portions, and the results of these tasks are combined to obtain the final result of the computation. To prevent external entities from accessing or reconstructing the tensor, the computing tasks are shuffled and distributed out of order. This partitioning and shuffling technique ensures the security of the tensor during the outsourcing process.

Original Abstract Submitted

Protection of access to a tensor in outsourcing deep learning computations via shuffling. For example, the tensor in the computation of an artificial neural network can be partitioned into portions of different sizes. The computing tasks can be generated for operating on the portions such that the results of the computing tasks can be combined to obtain the result of a computing task operates on the tensor in the computation of the artificial neural network. The computing tasks can be shuffled for distribution out of order to external entities. The partitioning and shuffling can prevent the external entities from accessing and/or reconstructing the tensor.