Схожие документы

• Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models
  по: Dang, Trung Cuong, и др.
  Опубликовано: (2025)
• Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting
  по: To, Bang Trinh Tran, и др.
  Опубликовано: (2025)
• Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
  по: Zhang, Xinyu, и др.
  Опубликовано: (2023)
• MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks
  по: Zhang, Fangyuan, и др.
  Опубликовано: (2024)
• Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack
  по: Zhou, Ying, и др.
  Опубликовано: (2024)