類似資料

• Exploring the limits of strong membership inference attacks on large language models
  著者:: Hayes, Jamie, 等
  出版事項: (2025)
• Protecting Classifiers From Attacks
  著者:: Gallego, Victor, 等
  出版事項: (2020)
• Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
  著者:: Zaree, Pedram, 等
  出版事項: (2025)
• Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
  著者:: Küchler, Nicolas, 等
  出版事項: (2025)
• Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States
  著者:: Chia, Xin Wei, 等
  出版事項: (2025)