Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models

Documenti analoghi

• Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
  di: Wang, Ningfei, et al.
  Pubblicazione: (2024)
• SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Driving
  di: Ma, Chen, et al.
  Pubblicazione: (2024)
• LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategies
  di: Sato, Takami, et al.
  Pubblicazione: (2023)
• T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving
  di: Ma, Chen, et al.
  Pubblicazione: (2025)
• Trapped by Their Own Light: Deployable and Stealth Retroreflective Patch Attacks on Traffic Sign Recognition Systems
  di: Tsuruoka, Go, et al.
  Pubblicazione: (2025)