A Modified Word Saliency-Based Adversarial Attack on Text Classification Models

Documenti analoghi

• Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent
  di: Waghela, Hetvi, et al.
  Pubblicazione: (2024)
• Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation
  di: Waghela, Hetvi, et al.
  Pubblicazione: (2024)
• Adversarial Robustness through Dynamic Ensemble Learning
  di: Waghela, Hetvi, et al.
  Pubblicazione: (2024)
• Adversarial Text Generation with Dynamic Contextual Perturbation
  di: Waghela, Hetvi, et al.
  Pubblicazione: (2025)
• Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks
  di: Waghela, Hetvi, et al.
  Pubblicazione: (2024)