RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things

by   Huming Qiu, et al.

Though deep neural network models exhibit outstanding performance for various applications, their large model size and extensive floating-point operations render deployment on mobile computing platforms a major challenge, and, in particular, on Internet of Things devices. One appealing solution is model quantization that reduces the model size and uses integer operations commonly supported by microcontrollers . To this end, a 1-bit quantized DNN model or deep binary neural network maximizes the memory efficiency, where each parameter in a BNN model has only 1-bit. In this paper, we propose a reconfigurable BNN (RBNN) to further amplify the memory efficiency for resource-constrained IoT devices. Generally, the RBNN can be reconfigured on demand to achieve any one of M (M>1) distinct tasks with the same parameter set, thus only a single task determines the memory requirements. In other words, the memory utilization is improved by times M. Our extensive experiments corroborate that up to seven commonly used tasks can co-exist (the value of M can be larger). These tasks with a varying number of classes have no or negligible accuracy drop-off on three binarized popular DNN architectures including VGG, ResNet, and ReActNet. The tasks span across different domains, e.g., computer vision and audio domains validated herein, with the prerequisite that the model architecture can serve those cross-domain tasks. To protect the intellectual property of an RBNN model, the reconfiguration can be controlled by both a user key and a device-unique root key generated by the intrinsic hardware fingerprint. By doing so, an RBNN model can only be used per paid user per authorized device, thus benefiting both the user and the model provider.



There are no comments yet.


page 1

page 6

page 8

page 9


Streamlined Deployment for Quantized Neural Networks

Running Deep Neural Network (DNN) models on devices with limited computa...

Fingerprinting Multi-exit Deep Neural Network Models via Inference Time

Transforming large deep neural network (DNN) models into the multi-exit ...

A Survey on Methods and Theories of Quantized Neural Networks

Deep neural networks are the state-of-the-art methods for many real-worl...

Constrained deep neural network architecture search for IoT devices accounting hardware calibration

Deep neural networks achieve outstanding results in challenging image cl...

Quantization Backdoors to Deep Learning Models

There is currently a burgeoning demand for deploying deep learning (DL) ...

NoisFre: Noise-Tolerant Memory Fingerprints from Commodity Devices for Security Functions

Given the ubiquity of memory in commodity electronic devices, fingerprin...

A General Approach for Using Deep Neural Network for Digital Watermarking

Technologies of the Internet of Things (IoT) facilitate digital contents...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.