Perturbation-enabled Deep Federated Learning for Preserving Internet of Things-based Social Networks

Abstract

Federated Learning (FL), as an emerging form of distributed machine learning, can protect participants’ private data from being substantially disclosed to cyber adversaries. It has potential uses in many large-scale, data-rich environments, such as the Internet of Things (IoT), Industrial IoT, Social Media, and the emerging SM 3.0. However, federated learning is susceptible to some forms of data leakage through model inversion attacks. Such attacks occur through the analysis of participants’ uploaded model updates. Model inversion attacks can reveal private data and potentially undermine some critical reasons for employing federated learning paradigms. This paper proposes novel differential privacy (DP)-based deep federated learning framework. We theoretically prove that our framework can fulfill DP’s requirements under distinct privacy levels by appropriately adjusting scaled variances of Gaussian noise. We then develop a Differentially Private Data-Level Perturbation (DP-DLP) mechanism to conceal any single data point’s impact on the training phase. Experiments on real-world datasets, specifically the social media 3.0, Iris, and Human Activity Recognition (HAR) datasets, demonstrate that the proposed mechanism can offer high privacy, enhanced utility, and elevated efficiency. Consequently, it simplifies the development of various DP-based FL models with different trade-off preferences on data utility and privacy levels.

Exploring Deep Federated Learning for the Internet of Things: A GDPR-Compliant Architecture

“…A novel DP-based DFL framework was proposed [85] that fulfilled DP's requirements under different privacy levels by adjusting scaled variances of Gaussian noise. The authors also developed a Differentially Private Data-Level Perturbation (DP-DLP) mechanism to conceal individual data points' impact on the training phase.…”

Revolutionizing AI-Assisted Education with Federated Learning: A Pathway to Distributed, Privacy-Preserving, and Debiased Learning Ecosystems

“…FL has demonstrated success in applications within the healthcare (Thwal et al 2021;Ng et al 2021;Lee et al 2021;Kumaresan, Kumar, and Muthukumar 2022;Lu et al 2022;Linardos et al 2022;Adnan et al 2022;Oldenhof et al 2023;Wu et al 2023) and social science/communication domains (He et al 2019;Shen, Gou, and Wu 2022;Salim et al 2022;Khelghatdoust and Mahdavi 2022); however, its impact is still underexplored in education domain. In particular, FL holds the potential to enhance AI-assisted education in several critical domains.…”