CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs

Documenti analoghi

• Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
  di: Zhang, Jiaming, et al.
  Pubblicazione: (2025)
• V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators
  di: Zhou, Jiazhou, et al.
  Pubblicazione: (2026)
• ALA: Naturalness-aware Adversarial Lightness Attack
  di: Huang, Yihao, et al.
  Pubblicazione: (2022)
• VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
  di: Tang, Yolo Y., et al.
  Pubblicazione: (2024)
• Adversarial Attack Against Images Classification based on Generative Adversarial Networks
  di: Yang, Yahe
  Pubblicazione: (2024)