Importance Aware Undervolting for Robust Neural Network Training
- 5 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. 11 (2) , 147-157
Abstract
Convolutional Neural Network (CNN) is a powerful tool that has been extensively applied to many different applications. However, recent developments at CNN have revealed its vulnerability against adversarial example attacks. By introducing visually undetectable noise to the input image, an adversarial example attack can cause the CNN classifier to make false predictions. Multiple approaches have been proposed to defend against adversarial samples, one of which focuses on injecting noise into CNN during training. However, the existing method cannot generate noise efficiently and introduces extra time and energy overhead. In this paper, we propose an Importance-Aware undervolting training framework to improve CNN robustness. The undervolting technique is employed during training for noise generation at negligible overhead. Meanwhile, we observe that the neuron importance and bit importance in hardware can be leveraged during undervolting CNN training for controllable and flexible noise injection, which improves robustness. We design a position-aware bit mapping method in the memory unit by allocating data bits based on significance. And an importanceaware processing element (PE) mapping is also proposed at the computation unit for noise restriction. Our approach regularizes the noise injected into CNN and serves as an efficient method to defend against adversarial example attacks with significant energy savings. The proposed framework is evaluated through both FPGA implementation and software simulation. The experiment results show that our importance-aware undervolting CNN training achieves 47.8% adversarial accuracy at PGD-10 attack and 47.0% training energy savings.Keywords
This publication has 18 references indexed in Scilit:
- Using Undervolting as an on-Device Defense Against Adversarial Machine Learning Attacks2021
- Ptolemy: Architecture Support for Robust Deep Learning2020
- Universal Adversarial Attack Via Enhanced Projected Gradient Descent2020
- Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack2019
- Comprehensive Evaluation of Supply Voltage Underscaling in FPGA on-Chip Memories2018
- Robust Physical-World Attacks on Deep Learning Visual Classification2018
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- Undervolting in Real World WSN Applications: A Long-Term Study2016
- Modeling Within-Die Spatial Correlation Effects for Process-Design Co-Optimization2005