P2TA: Privacy-preserving task allocation for edge computing enhanced mobile crowdsensing

Abstract

In conventional mobile crowdsensing (MCS) applications, the crowdsensing server (CS-server) needs mobile users’ precise locations for optimal task allocation, which raises privacy concerns. This paper proposes a privacy-preserving task allocation framework (called P2TA) for edge computing enhanced MCS, focusing on optimize task acceptance rate while protecting participants’ privacy by introducing edge nodes. The basic idea is that edge nodes act as task assignment agents with privacy protection that prevents an untrusted CS-server from accessing a user’s private data. We begin with a thorough analysis of the limitations of typical task allocation and obfuscation schemes. On this basis, the optimization problem about location obfuscation and task allocation is formulated in consideration of privacy constraints, travel distance and impact of location perturbation. Through problem decomposition, the location obfuscation subproblem is modeled as a leader-follower game between the designer of location obfuscation mechanism and the potential attacker. Against inference attack with background knowledge, a genetic algorithm is introduced to initialize an obfuscation matrix. With the matrix, an edge node makes task allocation decisions that maximize task acceptance rate subject to differential and distortion privacy constraints. The effectiveness and superiority of P2TA compared to exiting task allocation schemes are validated via extensive simulations.