Defending against Backdoors in Federated Learning with Robust Learning Rate

后门 计算机科学 对手 计算机安全 集合(抽象数据类型) 对抗制 方案(数学) 人工智能 数学 数学分析 程序设计语言
作者
Mustafa Safa Özdayi,Murat Kantarcıoğlu,Yulia R. Gel
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence (AAAI)]
卷期号:35 (10): 9268-9276 被引量:60
标识
DOI:10.1609/aaai.v35i10.17118
摘要

Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial attacks due to decentralized and unvetted data. One important line of attacks against FL is the backdoor attacks. In a backdoor attack, an adversary tries to embed a backdoor functionality to the model during training that can later be activated to cause a desired misclassification. To prevent backdoor attacks, we propose a lightweight defense that requires minimal change to the FL protocol. At a high level, our defense is based on carefully adjusting the aggregation server's learning rate, per dimension and per round, based on the sign information of agents' updates. We first conjecture the necessary steps to carry a successful backdoor attack in FL setting, and then, explicitly formulate the defense based on our conjecture. Through experiments, we provide empirical evidence that supports our conjecture, and we test our defense against backdoor attacks under different settings. We observe that either backdoor is completely eliminated, or its accuracy is significantly reduced. Overall, our experiments suggest that our defense significantly outperforms some of the recently proposed defenses in the literature. We achieve this by having minimal influence over the accuracy of the trained models. In addition, we also provide convergence rate analysis for our proposed scheme.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
传奇3应助ran123456采纳,获得30
刚刚
keyan_baby完成签到,获得积分20
1秒前
3秒前
坡坡大王完成签到,获得积分10
4秒前
钱宇成关注了科研通微信公众号
4秒前
5秒前
Zayro完成签到,获得积分10
6秒前
7秒前
自信雅琴发布了新的文献求助10
7秒前
anna发布了新的文献求助10
10秒前
CodeCraft应助Lu采纳,获得10
11秒前
11秒前
11秒前
Bressanone发布了新的文献求助10
12秒前
妙蛙完成签到,获得积分10
13秒前
14秒前
111111111发布了新的文献求助10
15秒前
妙蛙发布了新的文献求助10
17秒前
18秒前
爱笑紫菜发布了新的文献求助30
20秒前
20秒前
21秒前
李爱国应助111111111采纳,获得10
21秒前
tay发布了新的文献求助10
22秒前
科研通AI5应助ffff采纳,获得10
23秒前
过氧化氢发布了新的文献求助30
25秒前
感动黄豆发布了新的文献求助10
26秒前
钱宇成发布了新的文献求助10
26秒前
YJ888发布了新的文献求助10
26秒前
vincen91完成签到,获得积分10
30秒前
Leach完成签到 ,获得积分10
31秒前
长乐完成签到,获得积分10
32秒前
FashionBoy应助院士人启动采纳,获得10
36秒前
37秒前
37秒前
AptRank完成签到,获得积分10
38秒前
量子星尘发布了新的文献求助10
38秒前
焦糖布丁的滋味完成签到,获得积分10
38秒前
39秒前
隐形的觅波完成签到 ,获得积分10
40秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989115
求助须知:如何正确求助?哪些是违规求助? 3531367
关于积分的说明 11253688
捐赠科研通 3269986
什么是DOI,文献DOI怎么找? 1804868
邀请新用户注册赠送积分活动 882078
科研通“疑难数据库(出版商)”最低求助积分说明 809105