VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking

Documenti analoghi

• PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
  di: Fu, Jiyuan, et al.
  Pubblicazione: (2024)
• LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
  di: Fu, Jiyuan, et al.
  Pubblicazione: (2025)
• Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
  di: Fu, Jiyuan, et al.
  Pubblicazione: (2024)
• Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
  di: Wang, Jiafeng, et al.
  Pubblicazione: (2022)
• VideoPure: Diffusion-based Adversarial Purification for Video Recognition
  di: Jiang, Kaixun, et al.
  Pubblicazione: (2025)