Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework

Documenti analoghi

• Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
  di: Shao, Zedian, et al.
  Pubblicazione: (2026)
• EditTrack: Detecting and Attributing AI-assisted Image Editing
  di: Jiang, Zhengyuan, et al.
  Pubblicazione: (2025)
• Refusing Safe Prompts for Multi-modal Large Language Models
  di: Shao, Zedian, et al.
  Pubblicazione: (2024)
• Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
  di: Jiang, Zhengyuan, et al.
  Pubblicazione: (2025)
• Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding
  di: Jang, Jonggyu, et al.
  Pubblicazione: (2024)