Ehsan Nowroozi

Dr Ehsan Nowroozi PhD

Senior Lecturer in Cyber Security (Trustworthiness of AI)

Ehsan Nowroozi is a Senior Lecturer in Cyber Security and a researcher affiliated with the Centre for Sustainable Cyber Security (CS2) at the School of Computing and Mathematical Sciences, Faculty of Engineering and Science, University of Greenwich. His research primarily focuses on improving the reliability and trustworthiness of Artificial Intelligence (AI) with expertise in areas such as Adversarial Machine Learning, Adversarial Multimedia Forensics and Security, and Federated Learning (FL) security. His current studies explore innovative approaches to evaluating the cyber and privacy risks associated with AI, particularly within FL frameworks. He completed his Ph.D. in Information Engineering and Sciences at the University of Siena, Italy in 2020, where his research concentrated on machine learning techniques for image forensics in adversarial settings. Before his appointment at the University of Greenwich, he served as a Senior Lecturer in Cyber Security at Ravensbourne University London and as an Assistant Professor at Bahcesehir University. He also held positions as a Research Fellow/Postdoctoral Fellow at Queen's University Belfast, University of Siena, University of Padua, and Sabanci University.

He has disseminated his research through publications in prestigious journals, such as IEEE TNSM, IEEE TSC, IEEE TDSC, and Elsevier COSE, as well as other notable Springer and related journals. Furthermore, he showcased his work at renowned international conferences including IEEE CSR, IEEE ICASSP, IEEE ICIP, and various leading security conferences.

He has contributed to projects funded by prominent institutions, including DARPA, the U.S. Air Force Research Laboratory, Italian Ministry of University and Research, and Thales, UK. His work encompasses research on adversarial machine learning in image and network security domains, AI security, and formal verification.

He is a Senior Member of IEEE and is affiliated with the IEEE Young Professionals, IEEE Signal Processing Society, European Association for Signal Processing (EURASIP), and IEEE Information Forensics and Security (IFS). He also serves on the editorial board of IEEE Transactions on Network and Service Management (TNSM). Additionally, he serves as an EPSRC Research Grant Reviewer, primarily focusing on cybersecurity research grant proposals.

Computer science

Responsibilities within the university
  • Senior Lecturer in Cyber Security
  • Researcher with the Centre for Sustainable Cyber Security (CS2)

    • Journal Reviewer

  • Computer Networks (Elsevier), 2024 - Present
  • IEEE Transactions on Networks and Service Management, 2022 - Present
  • IEEE Transactions on Industrial Informatics, 2022 - Present
  • IEEE Transaction on Neural Networks and Learning Systems, Mar. 2021 - Present
  • EURASIP Journal on Information Security, Jun. 2020 - Present
  • Journal of Electronic Imaging – SPIE Digital Library. 11 Nov. 2018 - Present
  • Journal of Digital Investigation – Elsevier. 19 Nov. 2018 - Present
  • Journal of Information Security and Applications – Elsevier. 24 Sep. 2017 - Present

    • Conference Reviewer

  • 16th IEEE International Workshop on Information Forensics and Security (WIFS), ROME, Italy, December 2-5, 2024.
  • 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Signal Processing: The Foundation for True Intelligence, 14-19 Apr. 2024, COEX, Seoul, Korea.
  • 2nd International Conference on Machine Learning and Intelligent Systems (MLIS2020), South Korea, 2020.

    • Technical Committee (TC) Activity

  • IEEE IFS-TC (IEEE Information Forensics and Security Technical Committee), Oct. 2023 – Oct. 2026
  • Invited to serve as TPC member for ATC 2021 (2021 The 18th International Conference on Advanced and Trusted Computing)

Awards
  • Professor Zdzisław Pawlak Awards in the category of International Cooperation Award" at the 18th Conference on Computer Science and Intelligence Systems (FedCSIS2023), for the paper "Balancing Privacy and Accuracy in Federated Learning for Speech Emotion Recognition", Sep. 2023, Poland
  • Top-performing (UNISI) detection algorithms from MFC’17. The algorithms test by MediFor DARPA Nimble Challenge Evaluation, 2017

Recognition
  • Senior Member IEEE, 2022 - Present
  • Technical Member of IEEE Information Forensics and Security (IEEE IFS)
  • EPSRC Research Grant Reviewer

Research / Scholarly interests
  • Multimedia Forensics (in particular, Image Forensics)
  • AI for Security / Security for AI
  • Federated Learning
  • Machine/Deep Approaches Applied to Forensic Problems
  • Adversarial Machine Learning
  • Adversarial Multimedia Forensics
  • Biometric Security
  • Hardware Cryptography
  • Information Security
  • Explainable Artificial Intelligence

Research Projects

  • "Verification of AI" funded by Thales UK, Queen’s University Belfast, UK, 2023.
  • "Lighthouse: Securing the Transition Toward the Future Internet" funded by STARS 2019, University of Padua, Italy (Supervisor: Prof. Mauro Conti)
  • "Medifor: Media Forensics" project, funded by DARPA and the Air Force Research Laboratory (AFRL) under agreement number FA8750-16-2-0173. (Supervisor: Prof. Mauro Barni) - University of Siena, Italy
  • "PREMIER: Preserving Media trustworthiness in the artificial Intelligence ERA", project funded by the Italian Ministry of University and Research (MUR) under the PRIN 2017 2017Z595XS-001 (Supervisor: Prof. Mauro Barni) - University of Siena, Italy

Key funded projects

  • Postdoctoral Fellow researcher, "Verification of AI" funded by Thales UK, Queen’s University Belfast, UK, 2023.
  • Postdoctoral Fellow researcher, "Lighthouse: Securing the Transition Toward the Future Internet" funded by STARS 2019, University of Padua, Italy
  • Postdoctoral Fellow researcher, "Medifor: Media Forensics" project, funded by DARPA and the Air Force Research Laboratory (AFRL) under agreement number FA8750-16-2-0173.) - University of Siena, Italy
  • Postdoctoral Fellow researcher, "PREMIER: Preserving Media trustworthiness in the artificial Intelligence ERA", project funded by the Italian Ministry of University and Research (MUR) under the PRIN 2017 2017Z595XS-001- University of Siena, Italy.

Recent publications

Journal Papers:

  • Rahdari, A., Keshavarz, E., Nowroozi, E., Taheri, R., Hajizadeh, M., Mohammadi, M., Sinaei, S., and Bauscher, T., 2025. A survey on privacy and security in distributed cloud computing: Exploring federated learning and beyond. Submitted to IEEE Open Journal of the Communication Society.
  • Nowroozi, E., Haider, I., Taheri, R., and Conti, M., 2025. Federated learning under attack: Exposing vulnerabilities through data poisoning attacks in computer networks. IEEE Transactions on Network and Service Management.
  • Nowroozi, E., Jadalla, N., Ghelichkhani, S., and Jolfaei, A., 2024. Mitigating label flipping attacks in malicious URL detectors using ensemble trees. IEEE Transactions on Network and Service Management, 21, pp. 6875–6884.
  • Nowroozi, E., Mekdad, Y., Conti, M., Milani, S., and Uluagac, S., 2024. Real or virtual: A video conferencing background manipulation-detection system. Multimedia Tools and Applications.
  • Nowroozi, E., Mohammadi, M., Golmohammadi, P., Mekdad, Y., Conti, M., and Uluagac, A.S., 2024. Resisting deep learning models against adversarial attack transferability via feature randomization. IEEE Transactions on Services Computing, 17(1), pp. 18–29.
  • Taheri, R., Ghahremani, M., Nowroozi, E., and Dehghantanha, A., 2024. Statistical methods for mitigating data poisoning attacks against federated network intrusion detection systems. Submitted to IEEE Transactions on Dependable and Secure Computing.
  • R. Shrestha, M. Mohammadi, S. Sinaei, A. Salcines, D. Pampliega, R. Clemente, E. Nowroozi, and A. Lourdes Sanz, 2024. Anomaly detection based on LSTM and autoencoders using federated learning in smart electric grid. Journal of Parallel and Distributed Computing, 193, p. 104951.
  • Nowroozi, E., Habibi, Y., and Conti, M., 2024. SPRITZ-PS: Validation of synthetic face images using a large dataset of printed documents. Multimedia Tools and Applications, pp. 1–29.
  • Mohsen, E., Taheri, R., Nowroozi, E., Adda, M., and Cordeiro, L.C., 2024. SPLIT-IDS: Split learning-based intrusion detection system under label flipping attack. Submitted to IEEE Transactions on Network and Service Management.
  • Nowroozi, E., Mohammadi, M., Savaş, E., Mekdad, Y., and Conti, M., 2023. Employing deep ensemble learning for improving the security of computer networks against adversarial attacks. IEEE Transactions on Network and Service Management, 20(2), pp. 2096–2105.
  • Nowroozi, E., Abhishek, Mohammadi, M., and Conti, M., 2023. An adversarial attack analysis on malicious advertisement URL detection framework. IEEE Transactions on Network and Service Management, 20(2), pp. 1332–1344.
  • Nowroozi, E., Mekdad, Y., Berenjestanaki, M.H., Conti, M., and El Fergougui, A., 2022. Demystifying the transferability of adversarial attacks in computer networks. IEEE Transactions on Network and Service Management, 19(3), pp. 3387–3400.
  • Nowroozi, E., Dehghantanha, A., Parizi, R.M., and Choo, K.-K.R., 2021. A survey of machine learning techniques in adversarial image forensics. Computers & Security, 100, p. 102092.
  • Ferreira, A., Nowroozi, E., and Barni, M., 2021. VIPPrint: Validating synthetic image detection and source linking methods on a large-scale dataset of printed documents. Journal of Imaging, 7(3), p. 50.
  • Conti, M., Milani, S., Nowroozi, E., and Orazi, G., 2021. Do not deceive your employer with a virtual background: A video conferencing manipulation-detection system. arXiv preprint arXiv:2106.15130.
  • Barni, M., Nowroozi, E., and Tondi, B., 2020. Improving the security of image manipulation detection through one-and-a-half-class multiple classification. Multimedia Tools and Applications, 79, pp. 2383–2408.
  • Nowroozi, E. and Zakerolhosseini, A., 2015. Double JPEG compression detection using statistical analysis. Advances in Computer Science: An International Journal, 4(3), pp. 70–76.
  • Conference Papers:
  • Nowroozi, E., Taheri, R., Hajizadeh, M., & Bauschert, T., 2024. Verifying the robustness of machine learning-based intrusion detection against adversarial perturbation. IEEE International Conference on Cyber Security and Resilience (IEEE CSR), IEEE, London, United Kingdom.
  • Mohammadi, S., et al., 2023. Balancing privacy and accuracy in federated learning for speech emotion recognition. In: 18th Conference on Computer Science and Intelligence Systems (FedCSIS). IEEE, pp. 191-199.
  • Barni, M., Nowroozi, E., Tondi, B., & Zhang, B., 2020. Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 2977-2981.
  • Barni, M., Kallas, K., Nowroozi, E., & Tondi, B., 2020. CNN detection of GAN-generated face images based on cross-band co-occurrences analysis. In: IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, pp. 1-6.
  • Barni, M., Kallas, K., Nowroozi, E., & Tondi, B., 2019. On the transferability of adversarial examples against CNN-based image forensics. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 8286-8290.
  • Barni, M., Nowroozi, E., & Tondi, B., 2018. Detection of adaptive histogram equalization robust against JPEG compression. In: International Workshop on Biometrics and Forensics (IWBF). IEEE, pp. 1-8.
  • Barni, M., Costanzo, A., Nowroozi, E., & Tondi, B., 2018. CNN-based detection of generic contrast adjustment with JPEG post-processing. In: 25th IEEE International Conference on Image Processing (ICIP). IEEE, pp. 3803-3807.
  • Barni, M., Nowroozi, E., & Tondi, B., 2017. Higher-order, adversary-aware, double JPEG detection via selected training on attacked samples. In: 25th European Signal Processing Conference (EUSIPCO). IEEE, pp. 281-285.
  • Book/Book Chapters:
  • Nowroozi, E., Kallas, K., & Jolfaei, A., 2024. Adversarial multimedia forensics. In: Advances in Information Security. Vol. 104, Springer, pp. XVIII-284.
  • Nowroozi, E. & Mekdad, Y., 2023. Detecting high-quality GAN-generated face images using neural networks. In: Big Data Analytics and Intelligent Systems for Cyber Threat Intelligence. River Publishers, pp. 235-252.
  • Nowroozi, E., Seyedshoari, S., Mohammadi, M., & Jolfaei, A., 2022. Impact of media forensics and deepfake in society. In: Breakthroughs in Digital Biometrics and Forensics. Springer, pp. 387-410.
  • Nowroozi, E., Seyedshoari, S., Mekdad, Y., Savaş, E., & Conti, M., 2022. Cryptocurrency wallets: assessment and security. In: Blockchain for Cybersecurity in Cyber-Physical Systems. Springer, pp. 1-19.
  • Thesis:
  • E. Nowroozi, M. Barni, and B. Tondi, "Machine learning techniques for image forensics in adversarial setting," Ph.D. dissertation, 2020.

Patents

  • E. Nowroozi, “The deep learning method to strengthen computer network security”, Turkey Patent Appl. 2023/004922 (Submitted on 2023 and Granted on 2024).

Other research outputs are available on my Google Scholar.