A Perfect Match: Deep Learning Towards Enhanced Data Trustworthiness in Crowd-Sensing Systems

The advent of IoT edge devices has enabled the collection of rich datasets, as part of Mobile Crowd Sensing (MCS), which has emerged as a key enabler for a wide gamut of safety-critical applications ranging from traffic control, environmental monitoring to assistive healthcare. Despite the clear advantages that such unprecedented quantity of data brings forth, it is also subject to inherent data trustworthiness challenges due to factors such as malevolent input and faulty sensors. Compounding this issue, there has been a plethora of proposed solutions, based on the use of traditional machine learning algorithms, towards assessing and sifting faulty data without any assumption on the trustworthiness of their source. However, there are still a number of open issues: how to cope with the presence of strong, colluding adversaries while at the same time efficiently managing this high influx of incoming user data. In this work, we meet these challenges by proposing the hybrid use of Deep Learning schemes (i.e., LSTMs) and conventional Machine Learning classifiers (i.e. One-Class Classifiers) for detecting and filtering out false data points. We provide a prototype implementation coupled with a detailed performance evaluation under various (attack) scenarios, employing both real and synthetic datasets. Our results showcase how the proposed solution outperforms various existing resilient aggregation and outlier detection schemes.

I. Introduction

The emergence of resource-rich devices has changed the landscape of mobile sensing with multiple embedded sensors, e.g., accelerometers, cameras, etc. With more than 6 billion mobile subscriptions worldwide, these sensors (collectively) can be used to sense the environment and gather valuable data of unprecedented quality and quantity, practically from everywhere. This new sensing paradigm, Mobile Crowd Sensing (MCS) [1], makes individuals and user communities the focal point of the sensing infrastructure.