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

Abstract

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 safetycritical 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.

An Adaptive Temporal Convolutional Network Autoencoder for Malicious Data Detection in Mobile Crowd Sensing

“…A hybrid approach combining deep learning and classical machine learning is introduced for detecting and filtering out false data points in mobile crowdsensing (MCS) systems by Afzal-Houshmand et al [26]. The proposed approach is called FSD (forecastingbased sensor data filtering).…”

“…Existing studies have proposed various models for detecting malicious activities in MCS, primarily employing shallow machine learning algorithms [24][25][26][27][28][29]. The authors of [30] utilized a long short-term memory (LSTM) for malware detection in Android applications.…”

“…Table 1 summarizes the anomaly detection system reviewed in this section. [26] LSTM/SVM SensingBus MCS Munoz-Organero et al [27] DBN/KNN/SVM GPS Data MCS Venkatesh et al [28] Random Forest/DT/XGBoost SherLock Dataset MCS Memon et al [29] SVM/LR/Naïve Bayes SherLock Dataset MCS Zheng et al [30] Random Forest/ANN/LSTM SherLock Dataset MCS Our Proposed Model ATCN-AE SherLock Dataset MCS…”