GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

Documenti analoghi

• Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
  di: Guan, Jiwei, et al.
  Pubblicazione: (2026)
• Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
  di: Cheng, Shuyu, et al.
  Pubblicazione: (2024)
• SoK: Pitfalls in Evaluating Black-Box Attacks
  di: Suya, Fnu, et al.
  Pubblicazione: (2023)
• Towards Black-Box Membership Inference Attack for Diffusion Models
  di: Li, Jingwei, et al.
  Pubblicazione: (2024)
• Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry
  di: Salmani, Mahdi, et al.
  Pubblicazione: (2025)