The Center for Cybersecurity Research and Innovation (CCRI) at SUNY Polytechnic Institute is dedicated to advancing the state of cybersecurity through interdisciplinary research, education, and collaboration. CCRI focuses on developing innovative solutions for securing cyber-physical systems, smart grids, artificial intelligence systems, and emerging technologies. The Center serves as a hub for faculty, students, and industry partners to collaborate on addressing pressing cybersecurity challenges and fostering the next generation of cybersecurity professionals.
Research
CCRI’s research portfolio includes several active and upcoming projects aligned with national priorities in cybersecurity. Key areas include:
- Trustworthy Federated Learning for Smart Grids: Developing secure and privacy-preserving federated learning frameworks to detect anomalies in smart grid environments.
- Robust and Explainable Anomaly Detection: Designing AI-driven models that are both robust against adversarial attacks and interpretable to human operators.
- Defense Against Backdoor and Repetitive Attacks: Investigating defenses against stealthy poisoning attacks on machine learning models used in critical infrastructure.
- Reinforcement Learning for Smart Grid Security: Applying reinforcement learning to optimize security policies in real-time power system operations.
Research Professionals
Assistant Professor, Graduate Program Coordinator, and Founding Director of the Center for Cybersecurity Research and Innovation (CCRI), Department of Cybersecurity, SUNY Polytechnic Institute, Utica, NY, USA
Dr. Badr's research interests span several key areas of cybersecurity, including privacy preservation, trustworthy AI, machine learning in cybersecurity, cyber-physical system security, blockchain technology, and smart grid security. His work applies advanced machine learning techniques to tackle modern cybersecurity challenges, particularly those related to protecting critical infrastructures. Dr. Badr is the recipient of two competitive grants from the State University of New York as a lead Principal Investigator: a $32K seed grant to establish a research program in smart grid cybersecurity and a $250K grant to establish the Center for Cybersecurity Research and Innovation. He has authored over 40 research papers in leading journals and conferences, which have been cited more than 900 times. As the Graduate Program Coordinator, Dr. Badr oversees graduate students' academic and professional development in the cybersecurity program. Through his leadership at CCRI, he fosters research collaboration between academia and industry.
Lecturer, Department of Cybersecurity, SUNY Polytechnic Institute
Dr. Youssef’s expertise lies in engineering mathematics, computer engineering, and applied machine learning for complex network analysis. She has contributed to biomedical imaging, social network modeling, and multi-focus image fusion research with several peer-reviewed publications. An IEEE member and active academic contributor, Dr. Youssef supports CCRI’s educational and research objectives through teaching and interdisciplinary collaborations.
Assistant Professor and Undergraduate Program Coordinator, Department of Cybersecurity, SUNY Polytechnic Institute
Dr. Akhtar specializes in artificial intelligence-driven solutions for deepfakes, machine learning, biometrics, emotion recognition, and cybersecurity. He is an Associate Editor for IEEE Transactions on Artificial Intelligence and IEEE Access, and a Senior IEEE member. Recognized with multiple awards for outstanding editorial and research contributions, Dr. Akhtar brings deep expertise in AI applications within cybersecurity, supporting CCRI’s mission through research and interdisciplinary collaborations.
Professor, Department of Electrical and Computer Engineering, Tennessee Tech University, TN, USA
Dr. Mahmoud’s research centers on security and privacy in networks such as smart grids, blockchain, intelligent transportation, and cloud technology. With around 150 publications and over $6 million in external grants, including four NSF awards, he is a prominent figure in cybersecurity research. Dr. Mahmoud has received numerous awards for research and teaching excellence and mentored multiple graduate students. He serves as associate editor for IEEE Internet of Things and Springer’s Peer-to-Peer Networking journals.
Associate Professor, Department of Computer Science, Tennessee Tech University, TN, USA
Dr. Ismail has over 17 years of experience in cybersecurity and networking research, focusing on applications of AI and quantum information science in critical infrastructure protection and cyber-physical systems. He leads a research group of over 20 students and directs the NSF-funded Scholarship for Service program, ranked among the nation’s largest. Dr. Ismail serves as associate editor for several IEEE journals and is actively involved in major quantum computing initiatives, contributing valuable expertise to CCRI’s quantum cybersecurity efforts.
Co-Founder and CEO, Trout Software, Kingston, NY, USA
Mr. Doumenc brings over 7 years of cybersecurity industry experience, focusing on secure solutions for industrial and defense sectors. As CEO of Trout Software, he leads efforts to integrate security systems compliant with ISO27001 and NIST standards, supporting on-premises security and compliance management. Formerly a security engineer at Google, he provides CCRI with critical industry perspectives, enabling collaboration on practical cybersecurity solutions, SBIR proposals, and workforce development.
Publications and Scholarly Work
- K. Blazakis, N. Schetakis, M. M. Badr, D. Aghamalyan, and K. Stavrakakis, “Power Theft Detection in Smart Grids using Quantum Machine Learning,” IEEE Access, 2025.
- A. H. Bondok, M. M. Badr, M. Mahmoud, A. T. El-Toukhy, and M. Alsabaan, “A Trojan Attack against Smart Grid Federated Learning and Countermeasures,” IEEE Access, 2024.
- I. Elgarhy, M. M. Badr, M. Mahmoud, M. Alsabaan, T. Alshawi, and M. Alsaqhan, “XAI-Based Accurate Anomaly Detector That Is Robust Against Black-Box Evasion Attacks for the Smart Grid,” Applied Sciences, vol. 14, no. 21, Art. no. 9897, 2024.
- A. H. Bondok, M. Badr, M. Mahmoud, M. M. Fouda, and M. Abdullah, “Securing One-Class Federated Learning Classifiers Against Trojan Attacks in Smart Grid,” IEEE Internet of Things Journal, 2024.
- A. Bondok, O. Abdelsalam, M. Badr, M. Mahmoud, M. Alsabaan, and M. Alsaqhan, “Accurate Power Consumption Predictor and One-Class Electricity Theft Detector for Smart Grid ‘Change-and-Transmit’ Advanced Metering Infrastructure,” Applied Sciences, vol. 14, no. 20, Art. no. 9308, 2024.
- A. T. El-Toukhy, M. M. Badr, I. Elgarhy, M. Mahmoud, M. Alsabaan, and T. Alshawi, “Repetitive Backdoor Attacks and Countermeasures for Smart Grid Reinforcement Incremental Learning,” IEEE Internet of Things Journal, 2024.
- A. A. Elshazly, M. M. Badr, M. Mahmoud, W. Eberle, M. Alsabaan, and M. I. Ibrahem, “Reinforcement Learning for Fair and Efficient Charging Coordination for Smart Grid,” Energies, vol. 17, no. 18, Art. no. 4557, 2024.
- I. Elgarhy, M. M. Badr, M. Mahmoud, M. Nabil, M. Alsabaan, and M. I. Ibrahem, “Securing Smart Grid False Data Detectors Against White-Box Evasion Attacks Without Sacrificing Accuracy,” IEEE Internet of Things Journal, 2024.
- M. M. Badr, M. Baza, A. Rasheed, H. Kholidy, S. Abdelfattah, and T. S. Zaman, “Comparative Analysis Between Supervised and Anomaly Detectors Against Electricity Theft Zero-Day Attacks,” in Proc. Int. Telecommun. Conf. (ITC-Egypt), 2024, pp. 706–711.
- A. T. El-Toukhy, I. Elgarhy, M. M. Badr, M. Mahmoud, M. M. Fouda, and M. I. Ibrahem, “Securing Smart Grids: Deep Reinforcement Learning Approach for Detecting Cyber-Attacks,” in Proc. Int. Conf. Smart Appl., Commun. and Technol., 2024.
- A. Alshehri, M. M. Badr, M. Baza, and H. Alshahrani, “Deep Anomaly Detection Framework Utilizing Federated Learning for Electricity Theft Zero-Day Cyberattacks,” Sensors, vol. 24, no. 10, Art. no. 3236, 2024.