Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

Documenti analoghi

• Towards a Re-evaluation of Data Forging Attacks in Practice
  di: Suliman, Mohamed, et al.
  Pubblicazione: (2024)
• In-Context Probing for Membership Inference in Fine-Tuned Language Models
  di: Lu, Zhexi, et al.
  Pubblicazione: (2025)
• Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
  di: Kadhe, Swanand Ravindra, et al.
  Pubblicazione: (2024)
• Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications
  di: Zhang, Quan, et al.
  Pubblicazione: (2024)
• AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
  di: Ngong, Ivoline C., et al.
  Pubblicazione: (2026)