ConfusionPrompt: Practical Private Inference for Online Large Language Models

Documenti analoghi

• Split-and-Denoise: Protect large language model inference with local differential privacy
  di: Mai, Peihua, et al.
  Pubblicazione: (2023)
• SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
  di: Mai, Peihua, et al.
  Pubblicazione: (2025)
• POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
  di: Shao, Yangguang, et al.
  Pubblicazione: (2025)
• Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts
  di: Downey-Webb, Tiarnaigh, et al.
  Pubblicazione: (2025)
• Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model Prompts
  di: Peh, Steven
  Pubblicazione: (2025)