Hey, That's My Data! Token-Only Dataset Inference in Large Language Models

Ähnliche Einträge

• CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
  von: Xiong, Chen, et al.
  Veröffentlicht: (2025)
• Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
  von: Hu, Xiaomeng, et al.
  Veröffentlicht: (2024)
• Defining and Evaluating Physical Safety for Large Language Models
  von: Tang, Yung-Chen, et al.
  Veröffentlicht: (2024)
• Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
  von: Hu, Xiaomeng, et al.
  Veröffentlicht: (2025)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
  von: Xiong, Chen, et al.
  Veröffentlicht: (2026)