Quick and Accurate False Data Detection in Mobile Crowd Sensing

The attacks, faults, and severe communication/system conditions in Mobile Crowd Sensing (MCS) make false data detection a critical problem. Observing the intrinsic low dimensionality of general monitoring data and the sparsity of false data, false data detection can be performed based on the separation of normal data and anomalies. Although the existing separation algorithm based on Direct Robust Matrix Factorization (DRMF) is proven to be effective, requiring iteratively performing Singular Value Decomposition (SVD) for low-rank matrix approximation would result in a prohibitively high accumulated computation cost when the data matrix is large. In this work, we observe the quick false data location feature from our empirical study of DRMF, based on which we propose an intelligent Light weight Low Rank and False Matrix Separation algorithm (LightLRFMS) that can reuse the previous result of the matrix decomposition to deduce the one for the current iteration step. Depending on the type of data corruption, random or successive/mass, we design two versions of LightLRFMS. From a theoretical perspective, we validate that LightLRFMS only requires one round of SVD computation and thus has very low computation cost. We have done extensive experiments using a PM 2.5 air condition trace and a road traffic trace. Our results demonstrate that LightLRFMS can achieve very good false data detection performance with the same highest detection accuracy as DRMF but with up to 20 times faster speed thanks to its lower computation cost.

I. Introduction

The proliferation of smartphones contributes to the prosperity of a novel sensing paradigm called Mobile Crowd Sensing (MCS) [1]–[7]. Different from traditional wireless sensor networks (WSNs) which usually leverage dedicated sensors to acquire real-world conditions, MCS utilizes off-the-shelf smartphones carried by citizens to capture dynamic changes of social and urban information. The participatory and mobile nature of MCS provides a novel way for the monitoring of environment, transportation, and city infrastructure [8]–[11]. Although promising, there is a big challenge to ensure the data quality in MCS, as it is susceptible to different kinds of attacks, faults, severe communication and system conditions: •

Attack during transmission. With the transmissions over wireless networks, MCS data are subject to attacks such as eavesdropping, information tampering and malicious programs.

•

Attack by intelligent participation. MCS involves human participation. Intelligent attackers can introduce bad data into certain state variables, exploiting the knowledge of the MCS application configurations to bypass existing techniques for detecting bad measurements. For example, to earn rewards, participants may submit fake data without performing the actual sensing task [12], or compromise the mobile devices to provide faulty sensor readings [13].

•

Failure of algorithms or sensors. Mobile devices that do not work in normal states may also provide false measurements.

•

Severe communication/system conditions. False measurements may be resulted from network congestion, node misbehavior, monitor failure, and unreliable wireless transmission channels.