Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models

Documenti analoghi

• VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models
  di: Meftah, Hanene F. Z. Brachemi, et al.
  Pubblicazione: (2025)
• Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding
  di: Jang, Jonggyu, et al.
  Pubblicazione: (2024)
• SRAW-Attack: Space-Reweighted Adversarial Warping Attack for SAR Target Recognition
  di: Zhang, Yiming, et al.
  Pubblicazione: (2026)
• Efficient Visualization of Neural Networks with Generative Models and Adversarial Perturbations
  di: Karagounis, Athanasios
  Pubblicazione: (2024)
• Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging
  di: Thota, Poojitha, et al.
  Pubblicazione: (2024)