arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.02017cs.CRcs.LG
收藏

面向智能企业隐私保护的轻量级安全深度学习联邦学习模型

A Lightweight and Secure Deep Learning Model for Privacy-Preserving Federated Learning in Intelligent Enterprises

Reza Fotohi, Fereidoon Shams Aliee, Bahar Farahani

AI总结:

针对智能企业联邦学习面临的非独立同分布数据、隐私攻击及通信开销问题,提出轻量级安全的FedAnil+模型,通过三阶段方法显著提升了模型准确率并降低了通信与计算成本。

摘要:

不断增长的物联网连接推动了一种新型组织,即智能企业。在智能企业中,采用基于机器学习的模型从数据中提取洞察。由于这些传统模型的效率和隐私挑战,一种新的联邦学习(FL)范式应运而生。在FL中,多个企业可以联合训练模型以更新最终模型。然而,首先,FL训练的模型通常比集中式模型表现更差,特别是当企业训练数据是非独立同分布时。其次,由于FL的中心性和本地企业的不可信性,传统的FL解决方案容易受到中毒和推理攻击,并侵犯隐私。第三,企业和服务器之间参数的持续传输增加了通信成本。为此,提出了FedAnil+模型,这是一种新颖、轻量且安全的联邦深度学习模型,包含三个主要阶段。第一阶段的目标是解决数据类型分布偏斜挑战。第二阶段涵盖了针对中毒和推理攻击的隐私保护问题。最后,为了缓解通信开销,提出了一种新颖的压缩方法,显著减小了更新的规模。实验结果验证了FedAnil+在抵御推理和中毒攻击方面是安全的,且具有更好的准确性。此外,它在模型准确率(13%、16%和26%)、通信成本(17%、21%和25%)以及计算成本(7%、9%和11%)方面相比现有方法均有改进。

英文摘要:

The ever growing Internet of Things (IoT) connections drive a new type of organization, the Intelligent Enterprise. In intelligent enterprises, machine learning based models are adopted to extract insights from data. Due to the efficiency and privacy challenges of these traditional models, a new federated learning (FL) paradigm has emerged. In FL, multiple enterprises can jointly train a model to update a final model. However, firstly, FL trained models usually perform worse than centralized models, especially when enterprises training data is non-IID (Independent and Identically Distributed). Second, due to the centrality of FL and the untrustworthiness of local enterprises, traditional FL solutions are vulnerable to poisoning and inference attacks and violate privacy. Thirdly, the continuous transfer of parameters between enterprises and servers increases communication costs. To this end, the FedAnil+ model is proposed, a novel, lightweight, and secure Federated Deep Learning Model that includes three main phases. In the first phase, the goal is to solve the data type distribution skew challenge. Addressing privacy concerns against poisoning and inference attacks is covered in the second phase. Finally, to alleviate the communication overhead, a novel compression approach is proposed that significantly reduces the size of the updates. The experiment results validate that FedAnil+ is secure against inference and poisoning attacks with better accuracy. In addition, it shows improvements over existing approaches in terms of model accuracy (13%, 16%, and 26%), communication cost (17%, 21%, and 25%), and computation cost (7%, 9%, and 11%).

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。

↑