Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

Documenti analoghi

• Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models
  di: Tong, Ziyi, et al.
  Pubblicazione: (2025)
• Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models
  di: Golchin, Shahriar, et al.
  Pubblicazione: (2023)
• Investigating Data Contamination for Pre-training Language Models
  di: Jiang, Minhao, et al.
  Pubblicazione: (2024)
• Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
  di: Tao, Yongding, et al.
  Pubblicazione: (2025)
• Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  di: Puerto, Haritz, et al.
  Pubblicazione: (2024)