SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC

Documenti analoghi

• CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
  di: Luo, Jinglong, et al.
  Pubblicazione: (2024)
• SecDTD: Dynamic Token Drop for Secure Transformers Inference
  di: Cai, Yifei, et al.
  Pubblicazione: (2026)
• SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC
  di: Luo, Jinglong, et al.
  Pubblicazione: (2025)
• InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
  di: Tong, Meng, et al.
  Pubblicazione: (2023)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning
  di: Zhang, Zhuo, et al.
  Pubblicazione: (2024)