CyberAI Innovation: A Hands-on CyberAI Learning Platform for Malware Defense

Artificial intelligence (AI) is increasingly used to detect malware as it can identify new and evolving cyber threats faster than traditional signature-based approaches. However, cyber adversaries are also using AI to create sophisticated malware variants that can evade these detectors while preserving malicious functionality. This growing arms race creates an urgent need for a cybersecurity workforce that understands both AI-driven attacks and AI-enabled defenses. This project addresses that need by developing educational resources that prepare the next generation of cybersecurity professionals to defend against adversarial malware attacks. By combining curriculum innovation with hands-on training, the project will strengthen workforce readiness, improve cybersecurity education, and help address a critical national need for AI-literate cyber defenders. This project will develop a learning platform consisting of two integrated components: (1) an Adversarial Malware Generation and Defense (AMGD) curriculum and (2) an AMGD Workbench for experiential learning. The curriculum will define a body of knowledge at the intersection of adversarial machine learning, malware analytics, and AI-enabled cyber defense, informed by the NICE Cybersecurity Workforce Framework and continuous industry feedback from Rapid7. The curriculum will include modular learning units covering adversarial machine learning, malware detection and analysis, generative AI, ethical hacking, and robust system design. The AMGD Workbench will provide a safe, interactive environment where students can implement, benchmark, and analyze white-box and black-box adversarial malware attacks and defenses using Python notebooks and state-of-the-art techniques, including large language models, reinforcement learning, and genetic programming. The project will iteratively evaluate and refine both components through formative and summative assessment across University of Arizona and University of South Florida, reaching hundreds of students annually. Outcomes will be disseminated nationally through Cyber Florida and the Hawaii International Conference on System Sciences community to promote broad adoption. This project is supported by the CyberAICorps Scholarship for Service (CyberAI SFS) program which funds proposals to increase national capacity to educate and train professionals in Artificial Intelligence (AI) or Cybersecurity, and to support their placement and retention in the CyberAI mission of government organizations. The Scholarship Track funds academic institutions to award scholarships to students in exchange for their government service. The Innovation Track seeks transformative education proposals in the areas of AI, cybersecurity, or the integration of AI and cybersecurity. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.