Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems

Documenti analoghi

• Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
  di: Wang, Ningfei, et al.
  Pubblicazione: (2024)
• Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
  di: Sato, Takami, et al.
  Pubblicazione: (2023)
• Compromising Embodied Agents with Contextual Backdoor Attacks
  di: Liu, Aishan, et al.
  Pubblicazione: (2024)
• Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
  di: Li, Manling, et al.
  Pubblicazione: (2024)
• MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
  di: Fu, Dayuan, et al.
  Pubblicazione: (2024)