BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models

Documenti analoghi

• Do Spikes Protect Privacy? Investigating Black-Box Model Inversion Attacks in Spiking Neural Networks
  di: Poursiami, Hamed, et al.
  Pubblicazione: (2025)
• CatCMA with Margin for Single- and Multi-Objective Mixed-Variable Black-Box Optimization
  di: Hamano, Ryoki, et al.
  Pubblicazione: (2025)
• Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization
  di: Du, Yukun, et al.
  Pubblicazione: (2026)
• Illuminating the Black Box of Reservoir Computing
  di: Metzner, Claus, et al.
  Pubblicazione: (2025)
• PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization
  di: Duan, Qiqi, et al.
  Pubblicazione: (2022)