Keyed Chaotic Dynamics for Privacy-Preserving Neural Inference

TL;DR

This paper proposes a novel encryption method using key-conditioned chaotic graph dynamical systems to secure neural network inference, enhancing data privacy and authentication within neural architectures.

Contribution

It introduces a new encryption approach based on chaotic graph dynamical systems for neural inference, enabling secure data handling and authentication.

Findings

Enables encryption and decryption of real-valued tensors within neural networks.

Uses sensitivity to initial conditions for secure, key-dependent transformations.

Establishes a new paradigm for neural inference security.

Abstract

Neural network inference typically operates on raw input data, increasing the risk of exposure during preprocessing and inference. Moreover, neural architectures lack efficient built-in mechanisms for directly authenticating input data. This work introduces a novel encryption method for ensuring the security of neural inference. By constructing key-conditioned chaotic graph dynamical systems, we enable the encryption and decryption of real-valued tensors within the neural architecture. The proposed dynamical systems are particularly suited to encryption due to their sensitivity to initial conditions and their capacity to produce complex, key-dependent nonlinear transformations from compact rules. This work establishes a paradigm for securing neural inference and opens new avenues for research on the application of graph dynamical systems in neural network security.