AIFL: Ensuring Unlinkable Anonymity and Robust Incentive in Cross-Device Federated Learning

DOI码：

10.1109/JIOT.2024.3417003

发表刊物：

IEEE Internet of Things Journal

关键字：

Privacy;Federated learning;Internet of Things;Computational modeling;Training;Data models;Blockchains;Accountability;anonymity;federated learning (FL);incentive mechanism;Stackelberg game

摘要：

While cross-device federated learning (FL) offers a privacy-preserving data processing approach for Internet of Things (IoT) devices, it introduces fresh privacy risks and elevated computational expenses. Current solutions prioritize data privacy, often overlooking identity privacy vulnerabilities that may lead to personal information disclosure. In addition, achieving personalized client incentives while protecting identity privacy is a serious challenge. In this article, we propose AIFL, an unlinkable anonymity and robust incentive mechanism in cross-device FL. We design a threshold-based accountable ring signature (TARS) protocol that achieves unlinkable anonymity between identity and model updates and ensures accuracy and cost-effectiveness. AIFL identifies dishonest clients by incorporating a detection mechanism that leverages entropy weighting and cosine similarity for malicious update identification. Moreover, our robust incentive mechanism, grounded in the Stackelberg game, adopts differential pricing strategies that take into account clients’ anonymity budgets, ensuring equitable rewards. Performance evaluation reveals that AIFL achieves superior accuracy and robustness compared to Krum, even under 50% Byzantine attackers. Specifically, AIFL outperforms Krum by 0.32%, 29.1%, 79.17%, and 11.86% on MNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet data sets in nonindependent identically distributed, respectively. Additionally, AIFL effectively imposes costly penalties on dishonest clients and enhances the overall utility for honest clients. Consequently, the proposed AIFL holds significant implications for promoting secure and trustworthy machine learning in the IoT domain.

合写作者：

Gao Ying, Deng Huanghao

第一作者：

Chen Xiaofeng

论文类型：

期刊论文

通讯作者：

Gao Ying

卷号：

11

期号：

22

页面范围：

36688-36702

ISSN号：

2372-2541

是否译文：

否

发表时间：

2024-11-15