T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model

Documenti analoghi

• Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
  di: Zhang, Chenyu, et al.
  Pubblicazione: (2024)
• Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning
  di: Zhang, Chenyu, et al.
  Pubblicazione: (2025)
• Metaphor-based Jailbreak Attacks on Text-to-Image Models
  di: Zhang, Chenyu, et al.
  Pubblicazione: (2025)
• What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
  di: Zhang, Chenyu
  Pubblicazione: (2026)
• A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
  di: Ye, Mang, et al.
  Pubblicazione: (2025)