Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models

Documenti analoghi

• Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models
  di: Chu, Fengheng, et al.
  Pubblicazione: (2026)
• ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
  di: Xie, Jin, et al.
  Pubblicazione: (2025)
• TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
  di: Li, Songze, et al.
  Pubblicazione: (2024)
• Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography
  di: Li, Songze, et al.
  Pubblicazione: (2025)
• AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
  di: Reddy, Aashray, et al.
  Pubblicazione: (2025)