Vid-SME: Membership Inference Attacks against Large Video Understanding Models

Documenti analoghi

• Attention Prompting on Image for Large Vision-Language Models
  di: Yu, Runpeng, et al.
  Pubblicazione: (2024)
• NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
  di: Ren, Lingfeng, et al.
  Pubblicazione: (2026)
• MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems
  di: Yang, Peiru, et al.
  Pubblicazione: (2025)
• VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models
  di: Tang, Duoxun, et al.
  Pubblicazione: (2026)
• VidLeaks: Membership Inference Attacks Against Text-to-Video Models
  di: Wang, Li, et al.
  Pubblicazione: (2026)