Universal adversarial backdoor attacks to fool vertical federated learning

后门 计算机科学 任务(项目管理) 人工智能 机器学习 背景(考古学) 脆弱性(计算) 对抗制 计算机安全 数据挖掘 工程类 古生物学 系统工程 生物
作者
Peng Chen,Xin Du,Zhihui Lu,Hongfeng Chai
出处
期刊:Computers & Security [Elsevier BV]
卷期号:137: 103601-103601 被引量:1
标识
DOI:10.1016/j.cose.2023.103601
摘要

Vertical federated learning (VFL) is a privacy-preserving distribution learning paradigm that enables participants, owning different features of the same sample space to train a machine learning model collaboratively while retaining their data locally. This paradigm facilitates improved efficiency and security for participants such as financial or medical fields, making VFL an essential component of data-driven Artificial Intelligence 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 VFL sub-problems' universal trigger and model parameters. Our work distinguishes itself from existing studies on designing backdoor attacks for VFL, as those require the knowledge of auxiliary information that is not accessible within the split VFL architecture. In contrast, our approach does not require additional data to execute the attack. On the real-world 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 in revealing the hidden backdoor risks of VFL, hence paving the way for the future development of secure VFL. Our results in this paper make a major advance in revealing the hidden backdoor risks of VFL, hence paving the way for the future development of secure VFL applications such as finance.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
IRON完成签到,获得积分10
刚刚
Reese完成签到,获得积分10
刚刚
1秒前
1秒前
冷傲涑发布了新的文献求助10
1秒前
1秒前
1秒前
桐桐的应助被淡淡的冥茗采纳,获得10
2秒前
喝酸奶不要盖儿完成签到,获得积分10
2秒前
2秒前
chenjile发布了新的文献求助10
2秒前
molihuakai的应助被永沐华光采纳,获得10
3秒前
3秒前
3秒前
搜集达人的应助被花紫晴采纳,获得10
3秒前
4秒前
旷野完成签到,获得积分20
4秒前
顺利的冬士完成签到,获得积分10
4秒前
5秒前
5秒前
molihuakai的应助被zhawenchang采纳,获得10
5秒前
5秒前
Hello完成签到 ,获得积分10
5秒前
6秒前
SQC完成签到,获得积分20
6秒前
是群群喽发布了新的文献求助10
6秒前
null的应助被缥缈的芹采纳,获得10
7秒前
7秒前
科研通AI2S的应助被初景采纳,获得10
7秒前
现代的东蒽完成签到,获得积分10
8秒前
8秒前
张伟平完成签到,获得积分10
8秒前
8秒前
卜迷鹿发布了新的文献求助10
8秒前
8秒前
8秒前
9秒前
9秒前
xjc23发布了新的文献求助10
9秒前
所所的应助被keyan采纳,获得10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
John McDowells Bildungstheorie 800
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
Handbook of Pharmaceutical Excipients. 9th ed 400
Synthesis, Application and Future Perspectives of Smart Nano-materials - Part 1 400
Breaking the World 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8154217
求助须知:如何正确求助?哪些是违规求助? 9550722
关于积分的说明 21700876
捐赠科研通 7743358
什么是DOI,文献DOI怎么找? 3425651
关于科研通互助平台的介绍 2550897
邀请新用户注册赠送积分活动 2469372