Preventing DNN Model IP Theft via Hardware Obfuscation
- 28 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 11 (2) , 267-277
Abstract
Training accurate deep learning (DL) models require large amounts of training data, significant work in labeling the data, considerable computing resources, and substantial domain expertise. In short, they are expensive to develop. Hence, protecting these models, which are valuable storehouses of intellectual properties (IP), against model stealing/cloning attacks is of paramount importance. Today's mobile processors feature Neural Processing Units (NPUs) to accelerate the execution of DL models. DL models executing on NPUs are vulnerable to hyperparameter extraction via side-channel attacks and model parameter theft via bus monitoring attacks. This paper presents a novel solution to defend against DL IP theft in NPUs during model distribution and deployment/execution via lightweight, keyed model obfuscation scheme. Unauthorized use of such models results in inaccurate classification. In addition, we present an ideal end-to-end deep learning trusted system composed of: 1) model distribution via hardware root-of-trust and public-key cryptography infrastructure (PKI) and 2) model execution via low-latency memory encryption. We demonstrate that our proposed obfuscation solution achieves IP protection objectives without requiring specialized training or sacrificing the model's accuracy. In addition, the proposed obfuscation mechanism preserves the output class distribution while degrading the model's accuracy for unauthorized parties, covering any evidence of a hacked model.Keywords
Funding Information
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior–Brasil (CAPES)–Finance Code 0011
- National Council for Scientific and Technological Development–Brazil
This publication has 11 references indexed in Scilit:
- An Energy-Efficient Dual-Field Elliptic Curve Cryptography Processor for Internet of Things ApplicationsIEEE Transactions on Circuits and Systems II: Express Briefs, 2020
- How to Train Your Deep Multi-Object Tracker2020
- Compute Solution for Tesla's Full Self-Driving ComputerIEEE Micro, 2020
- Preventing Neural Network Model Exfiltration in Machine Learning Hardware Accelerators2018
- Reverse engineering convolutional neural networks through side-channel information leaks2018
- Stealing Hyperparameters in Machine Learning2018
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- Deep Residual Learning for Image Recognition2016
- PRINCE – A Low-Latency Block Cipher for Pervasive Computing Applications2012
- ImageNet: A large-scale hierarchical image database2009