An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models

Documenti analoghi

• Enhancing the robustness of vision transformer defense against adversarial attacks based on squeeze-and-excitation module
  di: YouKang Chang, et al.
  Pubblicazione: (2023-01-01)
• Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW
  di: William Villegas-Ch, et al.
  Pubblicazione: (2024-01-01)
• Adversarial attacks on spiking convolutional neural networks for event-based vision
  di: Julian Büchel, et al.
  Pubblicazione: (2022-12-01)
• Adversarial Attacks in Computer Vision: A Survey
  di: QIN Yingxin, ZHANG Kejia, PAN Haiwei, JU Yahao
  Pubblicazione: (2026-02-01)
• Theoretical Robustness Bounds on the Successful Adversarial Examples in Probabilistic Models: Comprehensive Insights From Gaussian Processes
  di: Hiroaki Maeshima, et al.
  Pubblicazione: (2026-01-01)