Tag: Privacy-Preserving Machine Learning

All the articles with the tag "Privacy-Preserving Machine Learning".

• CB-cPIR: Code-Based Computational Private Information Retrieval

  Published: 8 May, 2025 |  at  11:08 AM

  

  93.98 🤔

  CB-cPIR introduces a code-based single-server computational private information retrieval scheme that enhances security against subquery attacks by using high-weight secret vectors and dual queries, achieving lower communication and computational costs compared to lattice-based schemes like XPIR and SimplePIR.

• Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

  Published: 10 May, 2025 |  at  10:59 AM

  

  85.36 🤔

  This paper introduces a taxonomy of language model memorization into recitation, reconstruction, and recollection, demonstrating through experiments with Pythia models that different factors influence each category, with a taxonomy-based predictive model outperforming baselines in predicting memorization likelihood.

• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

  Published: 6 May, 2025 |  at  01:27 AM

  

  70.15 🤔

  本文提出了低秩知识遗忘（LoKU）框架，包含反向铰链损失（IHL）和 Fisher 加权低秩适配器初始化（FILA），以实现鲁棒且参数高效的大语言模型知识遗忘，有效移除敏感信息同时保持模型原有能力。

• Beyond Public Access in LLM Pre-Training Data

  Published: 4 May, 2025 |  at  04:32 PM

  

  53.67 🤔

  本文通過DE-COP成員推斷攻擊方法，使用O'Reilly書籍數據集證明OpenAI的GPT-4o可能訓練過非公共版權內容，突顯了LLM預訓練數據中非公共數據使用增加的趨勢及加強透明度和許可框架的必要性。