Saved in:
Bibliographic Details
Main Authors: Yang, Xiangli, Deng, Xijie, Zhang, Hanwei, Zou, Yang, Yang, Jianxi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.14232
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914842380599296
author Yang, Xiangli
Deng, Xijie
Zhang, Hanwei
Zou, Yang
Yang, Jianxi
author_facet Yang, Xiangli
Deng, Xijie
Zhang, Hanwei
Zou, Yang
Yang, Jianxi
contents Structural health monitoring (SHM) is critical to safeguarding the safety and reliability of aerospace, civil, and mechanical infrastructure. Machine learning-based data-driven approaches have gained popularity in SHM due to advancements in sensors and computational power. However, machine learning models used in SHM are vulnerable to adversarial examples -- even small changes in input can lead to different model outputs. This paper aims to address this problem by discussing adversarial defenses in SHM. In this paper, we propose an adversarial training method for defense, which uses circle loss to optimize the distance between features in training to keep examples away from the decision boundary. Through this simple yet effective constraint, our method demonstrates substantial improvements in model robustness, surpassing existing defense mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14232
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing robustness of data-driven SHM models: adversarial training with circle loss
Yang, Xiangli
Deng, Xijie
Zhang, Hanwei
Zou, Yang
Yang, Jianxi
Machine Learning
Artificial Intelligence
Structural health monitoring (SHM) is critical to safeguarding the safety and reliability of aerospace, civil, and mechanical infrastructure. Machine learning-based data-driven approaches have gained popularity in SHM due to advancements in sensors and computational power. However, machine learning models used in SHM are vulnerable to adversarial examples -- even small changes in input can lead to different model outputs. This paper aims to address this problem by discussing adversarial defenses in SHM. In this paper, we propose an adversarial training method for defense, which uses circle loss to optimize the distance between features in training to keep examples away from the decision boundary. Through this simple yet effective constraint, our method demonstrates substantial improvements in model robustness, surpassing existing defense mechanisms.
title Enhancing robustness of data-driven SHM models: adversarial training with circle loss
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.14232