Using Highly Compressed Gradients in Federated Learning for Data Reconstruction Attacks

计算机科学 初始化 压缩传感 水准点(测量) 压缩比 噪音(视频) 降噪 数据压缩 随机梯度下降算法 人工智能 人工神经网络 图像(数学) 内燃机 大地测量学 地理 程序设计语言 汽车工程 工程类
作者
Haomiao Yang,Mengyu Ge,Kunlan Xiang,Jingwei Li
出处
期刊:IEEE Transactions on Information Forensics and Security [Institute of Electrical and Electronics Engineers]
卷期号:18: 818-830 被引量:16
标识
DOI:10.1109/tifs.2022.3227761
摘要

Federated learning (FL) preserves data privacy by exchanging gradients instead of local training data. However, these private data can still be reconstructed from the exchanged gradients. Deep leakage from gradients (DLG) is a classical reconstruction attack that optimizes dummy data to real data by making the corresponding dummy and real gradients as similar as possible. Nevertheless, DLG fails with highly compressed gradients, which are crucial for communication-efficient FL. In this study, we propose an effective data reconstruction attack against highly compressed gradients, called highly compressed gradient leakage attack (HCGLA). In particular, HCGLA is characterized by the following three key techniques: 1) Owing to the unreasonable optimization objective of DLG in compression scenarios, we redesign a plausible objective function, ensuring that compressed dummy gradients are similar to the compressed real gradients. 2) Instead of simply initializing dummy data through random noise, as in DLG, we design a novel dummy data initialization method, Init-Generation, to compensate for information loss caused by gradient compression. 3) To further enhance reconstruction quality, we train an ad hoc denoising model using the methods of “first optimizing, next filtering, and then reoptimizing”. Extensive experiments on various benchmark data sets and mainstream models show that HCGLA is an effective reconstruction attack even against highly compressed gradients of 0.1%, whereas state-of-the-art attacks can only support 70% compression, thereby achieving a 700-fold improvement.
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
脑洞疼应助尧南采纳,获得10
1秒前
1秒前
1秒前
单纯代萱发布了新的文献求助30
1秒前
凯子哥完成签到,获得积分10
2秒前
星辰大海应助elever11采纳,获得10
2秒前
文艺涵菡发布了新的文献求助10
2秒前
闪闪梦曼完成签到,获得积分10
2秒前
微笑发布了新的文献求助10
3秒前
3秒前
月色完成签到,获得积分10
3秒前
肖亚鑫完成签到,获得积分10
3秒前
tingting发布了新的文献求助10
3秒前
空心胶囊完成签到,获得积分10
3秒前
4秒前
酷波er应助LamChem采纳,获得10
5秒前
共享精神应助ddd采纳,获得10
5秒前
蓝天阳光发布了新的文献求助10
5秒前
杨自强发布了新的文献求助10
5秒前
5秒前
Lucas应助kl采纳,获得10
5秒前
6秒前
铁柱xh完成签到 ,获得积分10
6秒前
在水一方应助健忘捕采纳,获得10
6秒前
之乡坞关注了科研通微信公众号
6秒前
7秒前
7秒前
小圈圈梦魇完成签到,获得积分10
7秒前
领导范儿应助英俊的若血采纳,获得10
7秒前
西大喜完成签到,获得积分10
8秒前
SciGPT应助Baneyhua采纳,获得10
8秒前
单纯代萱完成签到,获得积分10
8秒前
Lucas应助cwx采纳,获得10
8秒前
花花发布了新的文献求助10
9秒前
屹男发布了新的文献求助10
9秒前
10秒前
pzc发布了新的文献求助10
10秒前
天天快乐应助东哥采纳,获得10
11秒前
山神与你有约完成签到,获得积分10
11秒前
11秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
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 3969335
求助须知:如何正确求助?哪些是违规求助? 3514162
关于积分的说明 11172430
捐赠科研通 3249456
什么是DOI,文献DOI怎么找? 1794853
邀请新用户注册赠送积分活动 875437
科研通“疑难数据库(出版商)”最低求助积分说明 804809