A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models

Documenti analoghi

• Environment Maps Editing using Inverse Rendering and Adversarial Implicit Functions
  di: D'Orazio, Antonio, et al.
  Pubblicazione: (2024)
• Shedding More Light on Robust Classifiers under the lens of Energy-based Models
  di: Mirza, Mujtaba Hussain, et al.
  Pubblicazione: (2024)
• What is Adversarial Training for Diffusion Models?
  di: Rosaria, Briglia Maria, et al.
  Pubblicazione: (2025)
• Understanding Adversarial Training with Energy-based Models
  di: Mirza, Mujtaba Hussain, et al.
  Pubblicazione: (2025)
• Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense
  di: Bartolucci, Filippo, et al.
  Pubblicazione: (2024)