Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications

Documenti analoghi

• Edge-Only Universal Adversarial Attacks in Distributed Learning
  di: Rossolini, Giulio, et al.
  Pubblicazione: (2024)
• Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
  di: Rossolini, Giulio, et al.
  Pubblicazione: (2022)
• Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions
  di: Pietrosanti, Giulia Marchiori, et al.
  Pubblicazione: (2025)
• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
  di: Rossolini, Giulio, et al.
  Pubblicazione: (2022)
• CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models
  di: Nesti, Federico, et al.
  Pubblicazione: (2022)