PulseAugur
中
实时 13:04:01
English(EN) The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models

新的MIXGUARD框架增强了LLM分体式学习的隐私保护

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员推出了一种名为MIXGUARD的新框架，旨在增强大型语言模型（LLM）分体式学习中的隐私保护。该方法采用令牌级和表示级混淆，以及自适应梯度扰动，以在防止数据泄露给服务器的同时保持学习信号。实验表明，MIXGUARD实现了与非分体式训练相当的效用，并提供了更优越的隐私保护，抵御重构攻击。 AI

影响 通过实现分体式学习且不显著降低效用，增强了LLM训练的隐私保护。

排序理由 该集群包含一篇详细介绍LLM新方法的学术论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Chen Chen, Xiang Gao, Xianshun Wang, Chengran Li, Shengyu Xia, Xueluan Gong, Linru Zhang, Qian Wang, Kwok-Yan Lam ·

    The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models

    arXiv:2606.16801v1 Announce Type: new Abstract: Split learning provides a practical paradigm for resource-constrained users to train Large Language Models (LLMs) by offloading computation-intensive layers to a server while keeping raw data local. However, existing privacy-preserv…

  2. arXiv cs.CL TIER_1 English(EN) · Kwok-Yan Lam ·

    The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models

    Split learning provides a practical paradigm for resource-constrained users to train Large Language Models (LLMs) by offloading computation-intensive layers to a server while keeping raw data local. However, existing privacy-preserving split learning methods still face a difficul…

相关实体

相关话题