arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.11432cs.LG
收藏

云边协同中欺骗纵向联邦学习的通用对抗后门攻击

Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration

Fudan University(复旦大学);Engineering Research Center of Cyber Security Auditing and Monitoring, Ministry of Education(教育部网络安全审计与监控工程研究中心);Shanghai Blockchain Engineering Research Center(上海区块链工程研究中心);Institute of Financial Technology, Fudan University(复旦大学金融科技研究院)

Peng Chen, Xin Du, Zhihui Lu, Hongfeng Chai

AI总结:

针对云边协同 VFL 二分类场景,提出无需额外数据的 UAB 干净标签后门攻击,通过交替优化通用触发器与子问题参数注入后门,在两个数据集上达到最高 100% 攻击性能且不损害主任务。

摘要:

纵向联邦学习(VFL)是一种云边协作范式,使包含资源受限物联网(IoT)设备的边缘节点能够在将数据保留在本地的同时协同训练人工智能(AI)模型。该范式有助于提升边缘和物联网设备的隐私与安全性,使 VFL 成为人工智能物联网(AIoT)系统的重要组成部分。然而,VFL 的分割结构可能被攻击者利用以注入后门,使其能够操纵 VFL 的预测。本文旨在研究二分类任务背景下 VFL 的脆弱性。为此,我们定义了 VFL 中后门攻击的威胁模型,并提出一种通用对抗后门(UAB)攻击,以毒化 VFL 的预测。UAB 攻击由通用触发器生成和干净标签后门注入组成,在 VFL 训练期间的特定迭代中被纳入。这是通过交替优化通用触发器和 VFL 子问题的模型参数实现的。我们的工作不同于现有针对 VFL 设计后门攻击的研究,因为那些研究需要了解在分割式 VFL 架构中无法获取的辅助信息。相比之下,我们的方法执行攻击不需要任何额外数据。在 LendingClub 和 Zhongyuan 数据集上,我们的方法超越了现有最先进方法,在保持主任务性能的同时,实现了高达 100% 的后门任务性能。本文结果在揭示 VFL 隐藏后门风险方面取得重大进展,从而为未来安全 AIoT 的发展铺平道路。

英文摘要:

Vertical federated learning (VFL) is a cloud-edge collaboration paradigm that enables edge nodes, comprising resource-constrained Internet of Things (IoT) devices, to cooperatively train artificial intelligence (AI) models while retaining their data locally. This paradigm facilitates improved privacy and security for edges and IoT devices, making VFL an essential component of Artificial Intelligence of Things (AIoT) systems. Nevertheless, the partitioned structure of VFL can be exploited by adversaries to inject a backdoor, enabling them to manipulate the VFL predictions. In this paper, we aim to investigate the vulnerability of VFL in the context of binary classification tasks. To this end, we define a threat model for backdoor attacks in VFL and introduce a universal adversarial backdoor (UAB) attack to poison the predictions of VFL. The UAB attack, consisting of universal trigger generation and clean-label backdoor injection, is incorporated during the VFL training at specific iterations. This is achieved by alternately optimizing the universal trigger and model parameters of VFL sub-problems. Our work distinguishes itself from existing studies on designing backdoor attacks for VFL, as those require the knowledge of auxiliary information not accessible within the split VFL architecture. In contrast, our approach does not necessitate any additional data to execute the attack. On the LendingClub and Zhongyuan datasets, our approach surpasses existing state-of-the-art methods, achieving up to 100\% backdoor task performance while maintaining the main task performance. Our results in this paper make a major advance to revealing the hidden backdoor risks of VFL, hence paving the way for the future development of secure AIoT.

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。

↑