Secure mobile crowdsensing based on deep learning

Abstract

In order to stimulate secure sensing for Internet of Things (IoT) applications such as healthcare and traffic monitoring, mobile crowdsensing (MCS) systems have to address security threats, such as jamming, spoofing and faked sensing attacks, during both the sensing and the information exchange processes in large-scale dynamic and heterogenous networks. In this article, we investigate secure mobile crowdsensing and present how to use deep learning (DL) methods such as stacked autoencoder (SAE), deep neural network (DNN), and convolutional neural network (CNN) to improve the MCS security approaches including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DL-based approaches compared with traditional security schemes and identify the challenges that need to be addressed to implement them in practical MCS systems.

Mobile Crowd Sensing for Hypertensive Patient

“…In the article [6], research has been done to investigate secure data transmission in MCS network using Deep Learning (DL) algorithms such as stacked autoencoder, deep neural networks, convolutional neural networks, and deep reinforcement learning. The system also takes care of authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS.…”

Locally reconfigurable Self Organizing Feature Map for high impact malicious tasks submission in Mobile Crowdsensing

“…Research on the security and privacy of MCS has been conducting actively since MCS systems can be targets of attacks in various aspects [9] , [10] . Submission of altered / fake sensed data has been well investigated under the data poisoning attacks in MCS systems [11] as adversaries can inject fake / altered data in response to sensing tasks in order to gain rewards.…”

A Misbehaving-Proof Game Theoretical Selection Approach for Mobile Crowd Sourcing

“…MCS is vulnerable to external adversaries' attacks, such as spoofing and jamming, which aim to degrade or crash the service. These can be handled using network's security measures [7]. MCS is also vulnerable to internal misbehaving acts by malicious or selfish workers aiming to degrade the Quality of Service (QoS) of the tasks.…”

“…In the second layer, a game-theoretical approach based on Gale-Shapley is deployed to distribute the workers in the group amongst the tasks in the cluster such that the payoff of each task is maximized. The second layer also addresses the issue of the misbehaving act, where a worker uses multiple devices to impersonate multiple identities and maliciously change the majority-voting decision of a task [13], or selfishly maximize their profit. This layer is designed to detect and eliminate such misbehaving devices without invading the privacy of the participating workers.…”