Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry

Documenti analoghi

• RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
  di: Asif, Sadia, et al.
  Pubblicazione: (2026)
• Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
  di: Hu, Xulin, et al.
  Pubblicazione: (2026)
• LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
  di: Yang, Qin, et al.
  Pubblicazione: (2024)
• Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
  di: Wang, Fei, et al.
  Pubblicazione: (2025)
• Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
  di: Li, Qizhang, et al.
  Pubblicazione: (2024)