Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
CoRR(2024)
摘要
Deep Neural Networks (DNNs) have revolutionized a wide range of industries,
from healthcare and finance to automotive, by offering unparalleled
capabilities in data analysis and decision-making. Despite their transforming
impact, DNNs face two critical challenges: the vulnerability to adversarial
attacks and the increasing computational costs associated with more complex and
larger models. In this paper, we introduce an effective method designed to
simultaneously enhance adversarial robustness and execution efficiency. Unlike
prior studies that enhance robustness via uniformly injecting noise, we
introduce a non-uniform noise injection algorithm, strategically applied at
each DNN layer to disrupt adversarial perturbations introduced in attacks. By
employing approximation techniques, our approach identifies and protects
essential neurons while strategically introducing noise into non-essential
neurons. Our experimental results demonstrate that our method successfully
enhances both robustness and efficiency across several attack scenarios, model
architectures, and datasets.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要