Out-of-Distribution Detection Using Power-Side Channels for Improving Functional Safety of Neural Network FPGA Accelerators

Accurate out-of-distribution (OOD) detection is crucial for ensuring the safety and reliability of neural network (NN) accelerators in real-world scenarios. This paper proposes a novel OOD detection approach for NN FPGA accelerators using remote power side-channel measurements. We assess different m...

Full description

Saved in:
Bibliographic Details
Main Authors: Meyers, Vincent, Gnad, Dennis, Tahoori, Mehdi
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Image edge detection
neural network accelerators
out of distribution detection
Power measurement
power side channel
Safety
Sensors
System-on-chip
Voltage measurement
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate out-of-distribution (OOD) detection is crucial for ensuring the safety and reliability of neural network (NN) accelerators in real-world scenarios. This paper proposes a novel OOD detection approach for NN FPGA accelerators using remote power side-channel measurements. We assess different methods for distinguishing power measurements of in-distribution (ID) samples from OOD samples, comparing the effectiveness of simple power analysis and OOD sample identification based on the reconstruction error of an autoencoder (AE). Leveraging on-chip voltage sensors enables non-intrusive and concurrent remote OOD detection, eliminating the need for explicit labels or modifications to the underlying NN.
ISSN:1558-1101
DOI:10.23919/DATE58400.2024.10546836