ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts

Documenti analoghi

• SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization
  di: Liu, Houjun, et al.
  Pubblicazione: (2026)
• Brahe: A Modern Astrodynamics Library for Research and Engineering Applications
  di: Eddy, Duncan, et al.
  Pubblicazione: (2026)
• Optimal Ground Station Selection for Low-Earth Orbiting Satellites
  di: Eddy, Duncan, et al.
  Pubblicazione: (2024)
• Inferring Traffic Models in Terminal Airspace from Flight Tracks and Procedures
  di: Jung, Soyeon, et al.
  Pubblicazione: (2023)
• Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering
  di: Chaubard, Francois, et al.
  Pubblicazione: (2024)