TWR-STV: A Truthful Workers Recruitment with Sustainable Trust Verification for Service Enhancement in Mobile Crowd Sensing

Abstract

Mobile Crowd Sensing (MCS) has emerged a promising paradigm for large-scale data collection, which recruits truthful workers to enhance data quality, thereby maximizing the platform's profit. However, most existing work has the assumption that workers' trust remains stable once verified and truthful workers can consistently provide high-quality data. However, in real-world scenarios, there exist workers whose trust may change dynamically over time, which makes it difficult to ensure high-quality data collection due to the current lack of sustainable trust verification research, thereby damaging the platform's profit. To tackle the above challenge, we propose a novel Truthful Workers Recruitment with Sustainable Trust Verification (TWR-STV) scheme. The proposed TWR-STV scheme identifies the dynamic trust of workers and assesses the data value based on the quality of collected data, thereby selecting high-value workers to maximize the profit. First, we establish a dynamic trust model to capture the change in workers' trust. Second, we propose a stable and trustworthy worker identification method based on a two-layer sustainable data verification to identify workers' trust and the stability of workers' trust. Third, a multi-armed bandit-based stable and trustworthy worker recruitment scheme is proposed, in which high-value workers are recruited to increase platform profit and trustworthy workers who can be effectively verified are prioritized for recruitment to maintain sustainable trust verification. Furthermore, the proposed TWR-STV scheme takes into account the decay effect of time and trust on data value, which is more practical. Finally, we theoretically analyze the regret bound of TWR-STV and conduct experiments on a real dataset. Experimental results show that our proposed solution is superior to existing solutions in terms of total profit.