BERT ensemble based MBR framework for android malware detection

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 23, 2025

Predicting attacks in Android Malware (AM) devices within recommender systems-based IoT is challenging. A novel framework presented this study for AM Detection (AMD) using BERT Ensemble (MBR) and MobileNetV2. The MBR model uses a threat analysis technique to assess apps by subset of 100 permissions from 329 application-based permissions, together with refined feature set. Using MCADS, DroidRL, CNN, FAGnet, GAN, FEDriod, the performs exceptionally well, achieving 98% accuracy, 96% precision, recall, 97% F1-score, log loss 0.058. By leveraging their strengths, introduces significant innovation. ensemble methods on static data, not only provides reliable malware detection solution but also presents strategy. This research highlights potential applications dynamic evolving field addressing user privacy system security issues, despite growing risks IoT.

Language: Английский

A novel hybrid fuzzy logic and federated learning framework for enhancing cybersecurity and fraud detection in IoT-enabled metaverse transactions

Egyptian Informatics Journal, Journal Year: 2025, Volume and Issue: 30, P. 100668 - 100668

Published: April 24, 2025

Language: Английский

Regional coverage balance and efficient worker recruitment for self-organized mobile crowdsourcing

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 142, P. 109943 - 109943

Published: Dec. 30, 2024

Language: Английский