Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jung, Yoojin, Song, Byung Cheol
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.04747
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910905261883392
author Jung, Yoojin
Song, Byung Cheol
author_facet Jung, Yoojin
Song, Byung Cheol
contents Deep learning-based computer vision systems adopt complex and large architectures to improve performance, yet they face challenges in deployment on resource-constrained mobile and edge devices. To address this issue, model compression techniques such as pruning, quantization, and matrix factorization have been proposed; however, these compressed models are often highly vulnerable to adversarial attacks. We introduce the \textbf{Efficient Ensemble Defense (EED)} technique, which diversifies the compression of a single base model based on different pruning importance scores and enhances ensemble diversity to achieve high adversarial robustness and resource efficiency. EED dynamically determines the number of necessary sub-models during the inference stage, minimizing unnecessary computations while maintaining high robustness. On the CIFAR-10 and SVHN datasets, EED demonstrated state-of-the-art robustness performance compared to existing adversarial pruning techniques, along with an inference speed improvement of up to 1.86 times. This proves that EED is a powerful defense solution in resource-constrained environments.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models
Jung, Yoojin
Song, Byung Cheol
Computer Vision and Pattern Recognition
Deep learning-based computer vision systems adopt complex and large architectures to improve performance, yet they face challenges in deployment on resource-constrained mobile and edge devices. To address this issue, model compression techniques such as pruning, quantization, and matrix factorization have been proposed; however, these compressed models are often highly vulnerable to adversarial attacks. We introduce the \textbf{Efficient Ensemble Defense (EED)} technique, which diversifies the compression of a single base model based on different pruning importance scores and enhances ensemble diversity to achieve high adversarial robustness and resource efficiency. EED dynamically determines the number of necessary sub-models during the inference stage, minimizing unnecessary computations while maintaining high robustness. On the CIFAR-10 and SVHN datasets, EED demonstrated state-of-the-art robustness performance compared to existing adversarial pruning techniques, along with an inference speed improvement of up to 1.86 times. This proves that EED is a powerful defense solution in resource-constrained environments.
title Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.04747