Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification

Documenti analoghi

• Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game
  di: Xu, Qianqiao, et al.
  Pubblicazione: (2024)
• Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
  di: Ostermann, Simon, et al.
  Pubblicazione: (2024)
• Prompt Sentiment: The Catalyst for LLM Change
  di: Gandhi, Vishal, et al.
  Pubblicazione: (2025)
• Prompt Injection attack against LLM-integrated Applications
  di: Liu, Yi, et al.
  Pubblicazione: (2023)
• Jatmo: Prompt Injection Defense by Task-Specific Finetuning
  di: Piet, Julien, et al.
  Pubblicazione: (2023)