Enhancing Mobile Application Security through Mobile Crowd Sensing and Sourcing Solutions

Abstract

The market for Android applications has expanded dramatically, providing users with an ever-expanding array of functionality to meet a range of needs. Because mobile applications are so widely used, users are sharing more sensitive data, so protecting personal data is essential. However, this expansion has also led to a commensurate increase in cyber security threats, particularly for malware and adware that target mobile devices. To strengthen the mobile ecosystem, it is essential to divide mobile applications into discrete categories such as benign, adware, and malware. A unique sensing technique called Mobile Crowd Sensing/ Sourcing (MCS) uses users’ collective participation and their mobile devices to gather sensing data. Artificial intelligence (AI) approaches are used to make well-informed decisions that help optimize system performance as the MCS platform stores and processes vast amounts of data. The investigation primarily focuses on how AI is being applied to various MCS components, such as task distribution and data aggregation, to boost security and performance. Additionally, a novel categorization system that may be modified to compare research in this field is proposed in this paper. Because it makes it easier to identify attack surfaces that adversaries can exploit, this framework can be used to study AML in the context of MCS. It also highlights the potential vulnerabilities of AI-based MCS systems to adversarial attacks, which encourages future research to concentrate on designing resilient systems.