Project Grant 2422241

The National Science Foundation (NSF) awarded a $246,996 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the Rochester Institute of Technology (RIT) for the "Danger-IoT" project. The goal is to develop advanced machine learning models to detect heterogeneous malware across Internet-of-Things (IoT) systems. Key objectives include creating a generic malware detection model that works across diverse IoT platforms, ensuring efficiency for low-power devices, and enhancing robustness against sophisticated attacks. The project team, spanning four universities and three countries, is collaborating with industry experts to create open-source tools and datasets to benefit the broader community. Deliverables include novel methods for IoT malware detection, such as large-language model-based code-style transfer and multi-task learning with behavior classification. The project aims to address the growing threat of malware on the rapidly expanding IoT landscape, which is expected to reach one trillion devices by 2035.