arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.14898cs.CRcs.CL
收藏

安全地利用私有数据学习:面向大型语言模型的联邦学习框架

Safely Learning with Private Data: A Federated Learning Framework for Large Language Model

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing(未来区块链与隐私计算北京高精尖创新中心);Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);Beijing Academy of Blockchain and Edge Computing(北京区块链与边缘计算研究院)

JiaYing Zheng, HaiNan Zhang, LingXiang Wang, WangJie Qiu, HongWei Zheng, ZhiMing Zheng

AI总结:

本文提出面向LLM的联邦学习框架FL-GLM,通过本地部署输入输出块防梯度攻击、通信加密防逆向工程,并采用客户端批处理等优化提升效率,实现了与集中式chatGLM相当的性能。

摘要:

私有数据比公开数据规模更大、质量更高,能够极大地改进大型语言模型(LLM)。然而,由于隐私问题,这些数据通常分散在多个数据孤岛中,使其在LLM训练中的安全利用成为一项挑战。联邦学习(FL)是利用分布式私有数据训练模型的理想解决方案,但像FedAvg这样的传统框架由于对客户端的计算需求过高,不适用于LLM。另一种替代方案,拆分学习,将大部分训练参数卸载到服务器,同时在本地训练嵌入层和输出层,使其更适合LLM。尽管如此,它在安全性和效率方面面临重大挑战。首先,嵌入的梯度容易受到攻击,导致潜在的私有数据逆向工程。此外,服务器一次只能处理一个客户端训练请求的限制阻碍了并行训练,严重影响了训练效率。在本文中,我们提出了一个面向LLM的联邦学习框架,命名为FL-GLM,它能够防止由服务器端和对等客户端攻击引起的数据泄露,同时提高训练效率。具体而言,我们首先将输入块和输出块放置在本地客户端,以防止来自服务器的嵌入梯度攻击。其次,我们在客户端与服务器通信期间采用密钥加密,以防止来自对等客户端的逆向工程攻击。最后,我们采用诸如客户端批处理或服务器分层等优化方法,根据服务器的实际计算能力采用不同的加速方法。在NLU和生成任务上的实验结果表明,FL-GLM实现了与集中式chatGLM模型相当的指标,验证了我们联邦学习框架的有效性。

英文摘要:

Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utilization for LLM training a challenge. Federated learning (FL) is an ideal solution for training models with distributed private data, but traditional frameworks like FedAvg are unsuitable for LLM due to their high computational demands on clients. An alternative, split learning, offloads most training parameters to the server while training embedding and output layers locally, making it more suitable for LLM. Nonetheless, it faces significant challenges in security and efficiency. Firstly, the gradients of embeddings are prone to attacks, leading to potential reverse engineering of private data. Furthermore, the server's limitation of handle only one client's training request at a time hinders parallel training, severely impacting training efficiency. In this paper, we propose a Federated Learning framework for LLM, named FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks while improving training efficiency. Specifically, we first place the input block and output block on local client to prevent embedding gradient attacks from server. Secondly, we employ key-encryption during client-server communication to prevent reverse engineering attacks from peer-clients. Lastly, we employ optimization methods like client-batching or server-hierarchical, adopting different acceleration methods based on the actual computational capabilities of the server. Experimental results on NLU and generation tasks demonstrate that FL-GLM achieves comparable metrics to centralized chatGLM model, validating the effectiveness of our federated learning framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑