JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation

Documenti analoghi

• Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions
  di: Amini, Hadi, et al.
  Pubblicazione: (2025)
• FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model
  di: Mia, Md Jueal, et al.
  Pubblicazione: (2025)
• Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
  di: Hao, Shuyang, et al.
  Pubblicazione: (2024)
• AmorLIP: Efficient Language-Image Pretraining via Amortization
  di: Sun, Haotian, et al.
  Pubblicazione: (2025)
• DreamLIP: Language-Image Pre-training with Long Captions
  di: Zheng, Kecheng, et al.
  Pubblicazione: (2024)