REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective

Documenti analoghi

• Attacking Large Language Models with Projected Gradient Descent
  di: Geisler, Simon, et al.
  Pubblicazione: (2024)
• The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
  di: Wollschläger, Tom, et al.
  Pubblicazione: (2025)
• GemNet: Universal Directional Graph Neural Networks for Molecules
  di: Gasteiger, Johannes, et al.
  Pubblicazione: (2021)
• Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
  di: Schwinn, Leo, et al.
  Pubblicazione: (2025)
• Sampling-aware Adversarial Attacks Against Large Language Models
  di: Beyer, Tim, et al.
  Pubblicazione: (2025)