BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Documenti analoghi

• Evaluating Model-Agnostic Meta-Learning on MetaWorld ML10 Benchmark: Fast Adaptation in Robotic Manipulation Tasks
  di: Atamuradov, Sanjar
  Pubblicazione: (2025)
• ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval
  di: Syed, Shahram Najam, et al.
  Pubblicazione: (2025)
• ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
  di: Chen, Kewei, et al.
  Pubblicazione: (2026)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
  di: Zhou, Xueyang, et al.
  Pubblicazione: (2025)
• A Survey on Vision-Language-Action Models for Embodied AI
  di: Ma, Yueen, et al.
  Pubblicazione: (2024)