On-device Malware Detection using Performance-Aware and Robust Collaborative Learning
Hosted in Virtual Platform
Embedded and Cross-Layer Security
DescriptionThis paper presents collaborative machine learning (ML)-based malware detection framework. We introduce a) performance-aware precision-scaled federated learning (FL) to minimize the communication overheads with minimal device-level computations; and (2) a Robust and Active Protection with Intelligent Defense strategy against malicious activity (RAPID) at device and network-level due to malware and cyber-attacks. Deploying FL facilitates detecting malware attacks through collaborative learning and prevents data sharing thus ensuring data security and privacy. RAPID denies illegimate user and aids in developing an effective collaborative malware detection model. A comprehensive analysis, results and performance of proposed technique is presented along with the communication overheads.