Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures

TL;DR

This paper introduces a secure, efficient method for performing inference on Binarized Neural Networks within in-memory computing architectures by encrypting model parameters using a physical unclonable function, enabling secure and fast computation.

Contribution

It proposes a novel encryption strategy for BNN parameters in in-memory computing, combining physical unclonable functions with minimal overhead for secure inference.

Findings

Encrypted inference maintains high accuracy with minimal overhead.

Without the secret key, inference accuracy drops below 15%.

The method effectively secures BNNs in in-memory architectures.

Abstract

Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model parameters onto emerging non-volatile memory technologies, specifically using crossbar architectures, resulting in improved inference performance compared to traditional CMOS implementations. However, the common practice of protecting model parameters from theft attacks by storing them in an encrypted format and decrypting them at runtime introduces significant computational overhead, thus undermining the core principles of in-memory computing, which aim to integrate computation and storage. This paper presents a robust strategy for protecting BNN model parameters, particularly within in-memory computing frameworks. Our method utilizes a secret key derived from a physical unclonable function to transform model parameters prior to storage in the crossbar. Subsequently, the inference operations are performed on the encrypted weights, achieving a very special case of Fully Homomorphic Encryption (FHE) with minimal runtime overhead. Our analysis reveals that inference conducted without the secret key results in drastically diminished performance, with accuracy falling below 15%. These results validate the effectiveness of our protection strategy in securing BNNs within in-memory computing architectures while preserving computational efficiency.