US 2023/0401422 A1 · SYSTEMS AND METHODS FOR A FULL-STACK OBFUSCATION FRAMEWORK TO MITIGATE NEURAL NETWORK ARCHITECTURE THEFT

Abstract

A full-stack neural network obfuscation framework obfuscates a neural network architecture while preserving its functionality with very limited performance overhead. The framework includes obfuscating parameters or “knobs”, including layer branching, layer widening, selective fusion and schedule pruning, that increase the number of operators, reduce/increase the latency, and number of cache and DRAM accesses. In addition, a genetic algorithm-based approach is adopted to orchestrate the combination of obfuscating knobs to achieve the best obfuscating effect on the layer sequence and dimension parameters so that the architecture information cannot be successfully extracted.

Claims20

Dependent claims

A system for obfuscating the architecture of a neural network, comprising:

a processor in communication with a memory, the memory including instructions, which, when executed, cause the processor to:
access a neural network comprising a sequence of one or more layers, each layer in the sequence of one or more layers a plurality of dimension parameters;
access a plurality of obfuscation parameters for obfuscating the sequence of the one or more layers and the plurality of dimension parameters;
and
obfuscate execution of the neural network, including application by the processor of a plurality of obfuscating operations to the neural network during an execution process of the neural network based on the plurality of obfuscation parameters such that an execution trace of the neural network is altered.

2 more elements

Dependencies are inferred from the claim text.

Facts

Application

18/208,027Filed 9 Jun 2023

Priority

9 Jun 2022

Published

14 Dec 2023

Term ends

Not estimatedThe source records don’t support an estimate.

Classification9 codes

G06N 3/04
Neural networks: architecture, e.g. interconnection topology
G06N 3/0442
Recurrent networks, e.g. Hopfield networks: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
G06F 21/14
Protecting executable software: against software analysis or reverse engineering, e.g. by obfuscation
G06N 3/0464
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]

Systems and methods for a full-stack obfuscation framework to mitigate neural network architecture theft

Life of this patent

Systems and methods for a full-stack obfuscation framework to mitigate neural network architecture theft

Life of this patent

Abstract

Claims20