提升数据驱动的结构健康监测（SHM）模型的鲁棒性：结合circle loss的对抗训练
Enhancing robustness of data-driven SHM models: adversarial training with circle loss
AI总结：
针对结构健康监测中机器学习模型易受对抗样本攻击的问题，提出结合circle loss的对抗训练方法，通过优化特征距离使样本远离决策边界，显著提升了模型鲁棒性，优于现有防御机制。
摘要：
结构健康监测（SHM）对保障航空航天、土木和机械基础设施的安全与可靠性至关重要。随着传感器技术与计算能力的发展，基于机器学习的数据驱动方法在SHM领域得到广泛应用。然而，SHM中使用的机器学习模型易受对抗样本攻击——即使输入发生微小变化，也可能导致模型输出出现偏差。本文旨在通过探讨SHM中的对抗防御方法解决这一问题。文中提出了一种用于防御的对抗训练方法，该方法在训练中使用circle loss（圆形损失）优化特征间的距离，使样本远离决策边界。通过这种简单却有效的约束，该方法在模型鲁棒性上实现了显著提升，性能优于现有防御机制。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
