Researchers at the School of EECS at Washington State University are conducting cutting-edge security research across the entire computing stack spanning hardware, systems, software, and the web. Going beyond conventional approaches, they integrate cross-cutting AI and emerging cryptography concepts and methods in their research. The research is tightly intertwined with innovative cybersecurity education and training programs at the school and is driven by applications stemming from a variety of domains, including smart health systems, electronic design automation, power grids, and precision agriculture.

Support for the research comes from a wide variety of funding agencies including the U.S. Department of Defense, Department of Homeland Security, National Science Foundation, Department of Energy, and Department of Education. 

Key Topics

  • AI/ML and security:
    AI for cybersecurity and security of AI; anomaly detection for cybersecurity; adversarial attacks and defenses on AI models for different modalities; data poisoning attacks and defenses on AI models and LLMs for text/code; generative machine learning for intrusion detection systems; machine learning for synthetic cybersecurity data generation.
  • Software and systems security:
    Binary code composition analysis; security validation of code produced by generative AI; malware analysis of mobile/IoT apps and services; software supply chain security; graph models for code component analysis; machine learning for code attribution; visualization of software security and quality assurance.
  • Security of cyber-physical systems and critical infrastructure:
    Security for real-time systems, IoT, and cyber-physical systems; trustworthy ML for embedded/IoT systems; resilient real-time networks using SDNs; network science for security of complex systems; security for power grids; security for precision agriculture. 
  • Cryptography and post-quantum computing security:
    Lattice-based designs and analysis; zero-knowledge proofs; fully homomorphic encryptions (FHE); multi-party computation; secure protocols for privacy-preserving scenarios.
  • Web security and privacy:
    Web’s threat landscape analysis; development of privacy-preserving technologies; browser and web application security enhancements; authentication mechanism innovations; bot-prevention system robustness.
  • Hardware security:
    Security of hardware accelerators for AI applications; side-channel attacks; hardware Trojan detection and trusted IC design; physical unclonable functions.
  • Cybersecurity education:
    Workforce development frameworks; innovations in cybersecurity curricula; innovations in experiential learning programs.