Enhancing robustness of data-driven SHM models: adversarial training with circle loss

TL;DR

This paper proposes an adversarial training method using circle loss to improve the robustness of data-driven structural health monitoring models against adversarial examples, enhancing safety and reliability.

Contribution

It introduces a novel adversarial training approach with circle loss for SHM models, significantly improving their robustness over existing methods.

Findings

Enhanced model robustness against adversarial attacks

Outperforms existing defense mechanisms in experiments

Simple yet effective training constraint

Abstract

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.