When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models

Documenti analoghi

• CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models
  di: Liu, Shunchang, et al.
  Pubblicazione: (2025)
• Empirical Recipes for Efficient and Compact Vision-Language Models
  di: Huang, Jiabo, et al.
  Pubblicazione: (2026)
• Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
  di: Zhang, Naifu, et al.
  Pubblicazione: (2025)
• AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
  di: Li, Jiayu, et al.
  Pubblicazione: (2025)
• When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
  di: Lu, Hui, et al.
  Pubblicazione: (2025)