Federated Learning-Based Risk-Aware Decision to Mitigate Fake Task Impacts on Crowdsensing Platforms

Mobile crowdsensing (MCS) leverages distributed and non-dedicated sensing concepts by utilizing sensors embedded in a large number of mobile smart devices. However, the openness and distributed nature of MCS leads to various vulnerabilities and consequent challenges to address. A malicious user submitting fake sensing tasks to an MCS platform may be attempting to consume resources from any number of participants’ devices; as well as attempting to clog the MCS server. In this paper, a novel approach that is based on horizontal federated learning is proposed to identify fake tasks that contain a number of independent detection devices and an aggregation entity. Detection devices are deployed to operate in parallel with each device equipped with a machine learning (ML) module, and an associated training dataset. Furthermore, the aggregation module collects the prediction results from individual devices and determines the final decision with the objective of minimizing the prediction loss. Loss measurement considers the lost task values with respect to misclassification, where the final decision utilizes a risk-aware approach where the risk is formulated as a function of the utility loss. Experimental results demonstrate that using federated learning-driven illegitimate task detection with a risk aware aggregation function improves the detection performance of the traditional centralized framework. Furthermore, the higher performance of detection and lower loss of utility can be achieved by the proposed framework. This scheme can even achieve 100% detection accuracy using small training datasets distributed across devices, while achieving slightly over an 8% increase in detection improvement over traditional approaches.

I. Introduction

Mobile crowdsensing (MCS) is a cloud-inspired model for sensing, clustering and aggregating data via smart devices (e.g., smart phones, tablets, and in-vehicle sensors) and becomes an engaging topic [1]. Although MCS is applied in many areas, it confronts a number of security challenges and threats (e.g., data poisoning threat, privacy leakage and malware attack) [2]. Among them, a fake task attack is one of the top crucial threats where adversaries aim to clog the MCS servers and also drain resources from the devices that participate in the MCS campaigns [3]. Energy-oriented illegitimate tasks result in consuming excessive resources from users’ equipment such as energy, bandwidth and computation capability, which are all limited in capacity in such smart devices [4]. Furthermore, clogging MCS server via illegitimate task injection diminishes the effectiveness of the platform and suppresses users’ willingness to take part in MCS activities [4]. In order to protect both MCS platform and users from malicious activities of fake tasks, the studies in [5]– [7] proposed machine learning (ML)-based approaches to mitigate fake tasks in MCS platforms.