Ehsan Nowroozi is a prominent researcher and Senior member of the IEEE, known for his exceptional work in Cybersecurity. He currently serves as a research fellow at Queen’s University Belfast in Northern Ireland, specializing in adversarial machine learning and multimedia forensics. With a Ph.D. in Cybersecurity from the University of Siena, Italy, he focuses on understanding and mitigating vulnerabilities in AI systems, particularly against adversarial threats.
Following his Ph.D., Dr. Nowroozi continued research as a postdoctoral fellow at esteemed institutions, broadening his expertise in Cybersecurity. His primary research thrust involves countering security flaws in AI systems, developing robust defense mechanisms and mitigation strategies, and contributing significantly to the academic community through published papers and conferences.
Aside from research, Dr. Nowroozi actively contributes to the Cybersecurity community as a diligent reviewer for prestigious journals like IEEE Transactions on Network and Service Management, ensuring the quality and relevance of research publications in the field.
In 2022, he achieved Senior membership status in the IEEE, recognizing his dedication to excellence and impact in advancing AI-enabled Cybersecurity. Dr. Nowroozi remains devoted to driving advancements in the field, focusing on novel defense strategies against adversarial attacks in AI systems through collaborations with researchers and industry partners.
His expertise and commitment make him a key figure in the quest for secure AI technologies, benefiting both academia and industry in safeguarding against adversarial threats.
Education and Training
Postdoctoral Fellow, Sabanci University, Istanbul, Turkey, Department of Engineering and Natural Sciences, Computer Science and Engineering, Supervisors: Professor Erkay Savas, and Berrin Yanikoglu
Implementing a new Backdoor attacks to bypass a security model.
Fake Videoconferencing Detection
Designing a secure/robust model for discriminating real from virtual background and robust against adversarial attacks
Sec URL Model
Design a secure and robust model for distinguishing real URL from fake one and robust against adv attacks
Designing a model to avoid the adversarial transferability
Writing a book with a title of Adversarial Multimedia Forensics
Machine learning is an application of AI that enables systems to learn and improve from experience without being explicitly programmed. Machine learning focuses on developing computer programs that can access data and use it to learn for themselves.
Multimedia forensics has now become an integral part of the Cyber Forensics. Multimedia forensics involves the set of techniques used for the analysis of multimedia signals like audio, video, images. It aims to It aims to Reveal the history of digital content, Identifying the acquisition device that produced the data, Validating the integrity of the contents, Retrieving information from multimedia signals.
Adversarial machine learning
Is a machine learning that attempts to exploit models by taking advantage of obtainable model information and using it to create malicious attacks.
Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example.
is the practice and study of techniques for secure communication in the presence of adversarial behavior, an indispensable tool for protecting information in computer systems.
Adversarial attacks are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake
ORGANIZATIONS I AM INVOLVED
Get in touch with me...
I would be happy to talk to you if you need my assistance in your research or would like to collaborate on potential research projects. Please feel free to contact me using the contact information on the right. I would also be happy to meet you in person at my office, please drop me an e-mail to arrange a meeting time.