MODA: Model Ownership Deprivation Attack in Asynchronous Federated Learning

计算机科学 MNIST数据库 人工智能 异步通信 深度学习 计算机安全 机器学习 计算机网络
作者
Xiaoyu Zhang,Shen Lin,Chao Chen,Xiaofeng Chen
出处
期刊:IEEE Transactions on Dependable and Secure Computing [IEEE Computer Society]
卷期号:21 (4): 4220-4235 被引量:9
标识
DOI:10.1109/tdsc.2023.3348204
摘要

Training a deep learning model from scratch requires a great deal of available labeled data, computation resources, and expert knowledge. Thus, the time-consuming and complicated learning procedure catapulted the trained model to valuable intellectual property (IP), spurring interest from attackers in model copyright infringement and stealing. Recently, a new defense approach leverages watermarking techniques to inject watermarks into the training procedure and verify model ownership when necessary. To our best knowledge, there is no research work on model ownership stealing attacks in federated learning, and the existing defense or mitigation methods can not be directly used for federated learning scenarios. In this paper, we introduce watermarking neural networks in asynchronous federated learning and propose a novel model privacy attack, dubbed model ownership deprivation attack (MODA). MODA is launched by an inside adversarial participant, targeting occupying and depriving the remaining participants' (victims) copyright to achieve his maximum profit. The extensive experimental results on five benchmark datasets (MNIST, Fashion-MNIST, GTSRB, SVHN, CIFAR10) show that MODA is highly effective in a two-participant learning scenario with a minor impact on model's performance. When extending MODA into multiple participants scenario, MODA still maintains high attack success rate and classification accuracy. Compared to the state-of-the-art works, MODA has a higher attack success rate than the black-box solution and comparable efficacy with the approach in the white-box scenario.
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
任斯发布了新的文献求助10
刚刚
黄金蛋饺发布了新的文献求助10
刚刚
pluto应助科研通管家采纳,获得10
1秒前
春悠然应助科研通管家采纳,获得10
1秒前
高高应助科研通管家采纳,获得10
2秒前
高高应助科研通管家采纳,获得10
2秒前
情怀应助科研通管家采纳,获得10
2秒前
春悠然应助科研通管家采纳,获得10
2秒前
漂亮明辉完成签到,获得积分10
2秒前
CipherSage应助科研通管家采纳,获得10
2秒前
Wind应助科研通管家采纳,获得10
2秒前
xx完成签到,获得积分10
2秒前
搜集达人应助科研通管家采纳,获得10
2秒前
高高应助科研通管家采纳,获得10
2秒前
Jasper应助科研通管家采纳,获得30
2秒前
3秒前
高高应助科研通管家采纳,获得10
3秒前
3秒前
3秒前
3秒前
momo末流主发布了新的文献求助10
4秒前
zf发布了新的文献求助10
4秒前
昭昭完成签到,获得积分10
5秒前
LL完成签到,获得积分10
6秒前
SYLH应助苹果采纳,获得20
7秒前
yaoweiqi完成签到,获得积分10
7秒前
lh0907发布了新的文献求助10
7秒前
andngf发布了新的文献求助10
7秒前
123完成签到,获得积分20
7秒前
典雅听枫发布了新的文献求助10
9秒前
9秒前
11秒前
Gino完成签到,获得积分0
11秒前
科研通AI5应助初(*^▽^*)心采纳,获得10
12秒前
12秒前
zf完成签到,获得积分10
12秒前
SH123完成签到,获得积分10
13秒前
佛人世间完成签到,获得积分10
13秒前
14秒前
14秒前
高分求助中
(禁止应助)【重要!!请各位详细阅读】【科研通的精品贴汇总】 10000
Semantics for Latin: An Introduction 1099
Biology of the Indian Stingless Bee: Tetragonula iridipennis Smith 1000
Robot-supported joining of reinforcement textiles with one-sided sewing heads 740
镇江南郊八公洞林区鸟类生态位研究 500
Thermal Quadrupoles: Solving the Heat Equation through Integral Transforms 500
Corpus Linguistics for Language Learning Research 300
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 4139320
求助须知:如何正确求助?哪些是违规求助? 3676275
关于积分的说明 11620352
捐赠科研通 3370382
什么是DOI,文献DOI怎么找? 1851340
邀请新用户注册赠送积分活动 914489
科研通“疑难数据库(出版商)”最低求助积分说明 829266