When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models

Documenti analoghi

• VACoDe: Visual Augmented Contrastive Decoding
  di: Kim, Sihyeon, et al.
  Pubblicazione: (2024)
• UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models
  di: Lee, Segyu, et al.
  Pubblicazione: (2026)
• Active Prompt Learning in Vision Language Models
  di: Bang, Jihwan, et al.
  Pubblicazione: (2023)
• FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning
  di: Kim, Seongyoon, et al.
  Pubblicazione: (2024)
• Generative Visual Code Mobile World Models
  di: Koh, Woosung, et al.
  Pubblicazione: (2026)