類似資料

• Stealing User Prompts from Mixture of Experts
  著者:: Yona, Itay, 等
  出版事項: (2024)
• In-Context Representation Hijacking
  著者:: Yona, Itay, 等
  出版事項: (2025)
• Buffer Overflow in Mixture of Experts
  著者:: Hayes, Jamie, 等
  出版事項: (2024)
• UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
  著者:: Shumailov, Ilia, 等
  出版事項: (2024)
• Beyond Slow Signs in High-fidelity Model Extraction
  著者:: Foerster, Hanna, 等
  出版事項: (2024)