TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models

Documenti analoghi

• Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
  di: Song, Tianle, et al.
  Pubblicazione: (2025)
• Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents
  di: Yang, Yulong, et al.
  Pubblicazione: (2024)
• The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
  di: Liu, Mingrui, et al.
  Pubblicazione: (2025)
• A Survey on Adversarial Machine Learning for Code Data: Realistic Threats, Countermeasures, and Interpretations
  di: Yang, Yulong, et al.
  Pubblicazione: (2024)
• LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection
  di: Tian, Jiwei, et al.
  Pubblicazione: (2024)