.png){kind=icon}
返回
Shielding Collaborative Learning: Mitigating Poisoning Attacks Through Client-Side Detection
.png){kind=icon}
OA
AI
DOI：10.1109/TDSC.2020.2986205.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Collaborative learning allows multiple clients to train a joint model without sharing their data with each other. Each client performs training locally and then submits the model updates to a central server for aggregation. Since the server has no visibility into the process of generating the updates, collaborative learning is vulnerable to poisoning attacks where a malicious client can generate a poisoned update to introduce backdoor functionality to the joint model. The existing solutions for detecting poisoned updates, however, fail to defend against the recently proposed attacks, especially in the non-IID (independent and identically distributed) setting. In this article, we present a novel defense scheme to detect anomalous updates in both IID and non-IID settings. Our key idea is to realize client-side cross-validation, where each update is evaluated over other clients' local data. The server will adjust the weights of the updates based on the evaluation results when performing aggregation. To adapt to the unbalanced distribution of data in the non-IID setting, a dynamic client allocation mechanism is designed to assign detection tasks to the most suitable clients. During the detection process, we also protect the client-level privacy to prevent malicious clients from knowing the participations of other clients, by integrating differential privacy with our design without degrading the detection performance. Our experimental evaluations on three real-world datasets show that our scheme is significantly robust to two representative poisoning attacks.
Keyword:
Collaborative work
Data models
Servers
Computational modeling
Training
Task analysis
Training data
Poisoning attack
collaborative learning
deep learning
privacy
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.5
论文数:
2.4K
被引数:
9.6K
机构
引用论文
分享收藏分享收藏
分享收藏The Security of Autonomous Driving: Threats, Defenses, and Future Directions自动驾驶的安全性: 威胁、防御和未来方向.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容