mlsanityData to 7 Oct 2026

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

arXiv 2406.14232 ↗First posted 20 Jun 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 67 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

43 of 67 references.

References · 43

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  11. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  12. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
31 more
  1. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  3. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  4. 2017Countering Adversarial Images using Input Transformationscited by 517
  5. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  6. 2013Do Deep Nets Really Need to be Deep?cited by 466
  7. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  8. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  9. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  10. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  11. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  12. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  13. 2017On Detecting Adversarial Perturbationscited by 232
  14. 2018Adversarial Logit Pairingcited by 224
  15. 2021Data Augmentation Can Improve Robustnesscited by 193
  16. 2018Robustness via curvature regularization, and vice versacited by 174
  17. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  18. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  19. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  20. 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 98
  21. 2019Metric Learning for Adversarial Robustnesscited by 77
  22. 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
  23. 2023Data Augmentation Alone Can Improve Adversarial Trainingcited by 43
  24. 2021Adversarial Robustness with Semi-Infinite Constrained Learningcited by 39
  25. 2015Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimizationcited by 32
  26. 2018Lipschitz regularized Deep Neural Networks generalize and are adversarially robustcited by 19
  27. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
  28. 2019Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Losscited by 13
  29. 2018Divide, Denoise, and Defend against Adversarial Attackscited by 12
  30. 2020A Hierarchical Deep Convolutional Neural Network and Gated Recurrent Unit Framework for Structural Damage Detectioncited by 3
  31. 2021Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustnesscited by 2

Built on by

Not cited yet.