Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints

Documenti analoghi

• Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms
  di: Nöther, Jonathan, et al.
  Pubblicazione: (2025)
• MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems
  di: Nöther, Jonathan, et al.
  Pubblicazione: (2026)
• Policy Teaching via Data Poisoning in Learning from Human Preferences
  di: Nika, Andi, et al.
  Pubblicazione: (2025)
• Learning Embeddings for Sequential Tasks Using Population of Agents
  di: Mahajan, Mridul, et al.
  Pubblicazione: (2023)
• Corruption-Robust Offline Two-Player Zero-Sum Markov Games
  di: Nika, Andi, et al.
  Pubblicazione: (2024)