Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers

Documenti analoghi

• A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
  di: Fang, Tianmeng, et al.
  Pubblicazione: (2026)
• Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
  di: Liu, Ming, et al.
  Pubblicazione: (2025)
• Backdoor Attack with Sparse and Invisible Trigger
  di: Gao, Yinghua, et al.
  Pubblicazione: (2023)
• AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
  di: Jiang, Bo, et al.
  Pubblicazione: (2025)
• BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
  di: Bai, Jiawang, et al.
  Pubblicazione: (2023)