Research

His research expertise include (adversarial) image and multimedia forensics, adversarial machine learning, image forensics, network security. He is a member of the IEEE Young Professionals and IEEE Signal Processing Society.

Journal and Conference Reviewer

  • IEEE Transaction on Neural Networks and Learning Systems, March 2021 - present

  • EURASIP Journal on Information Security, June 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

  • The 2nd International Conference on Machine Learning and Intelligent Systems (MLIS2020), South Korea, 2020.

Select Publications

Published Papers
  • A. Ferreira, E. Nowroozi, and M. Barni (2021). VIPPrint: Validating Synthetic Image Detection and Source Linking Methods on a Large Scale Dataset of Printed Images, MDPI Journal of Imaging.

  • E. Nowroozi, A. Dehghantanha, R. M. Parizi, and Kim-Kwang R. Choo (2020). A Survey of Machine Learning Techniques in Adversarial Image Forensics, In Computers and Security Elsevier

  • M. Barni, E. Nowroozi, and B. Tondi (2019).Improving the Security of Image Manipulation Detection through one-and-a-half-class Multiple Classification., An International Journal of Multimedia Tools and Application (Springer)

  • E. Nowroozi (2015) Identification of Double Compressed Mediacal Images with Manipulation, Indian Journal of Fundamental and Applied Life Sciences

  • E. Nowroozi, and A. Zakerolhosseini (2015) Double JPEG Compression Detection Using Statistical Analysis , In Advances in Computer Science: An International Journal (ACSIJ)

  • M. Barni, K. Kallas, E. Nowroozi, and B. Tondi (2020) CNN Detection of GAN=Generated Face Images based on Cross-Band Co-occurrences Analysis , In 12 IEEE International Workshop on Information forensics and Security (WIFS), New York, USA

  • M. Barni, E. Nowroozi, B. Tondi, and B. Zhang (2020) Effectiveness of random deep feature selection for securing image manipulation detectors agasint adversarial examples , In 45th International on Acoustics, Speech, and Signal Processing, Barcelona, Spain

  • M. Barni, K. Kallas, E. Nowroozi, and B. Tondi (2019) On the Transferability of Adversarial Examples Against CNN-based Image Forensics , In 44th International on Acoustics, Speech, and Signal Processing, Brighton, UK

  • M. Barni, A. Costanzo, E. Nowroozi, and B. Tondi (2018) CNN-based Detection of Generic Contrast Adjustement with JPEG Post-Processing , In the IEEE International Conference on Image Processing (ICIP), Athens, Greece

  • M. Barni, E. Nowroozi, and B. Tondi (2018) Detection of Adaptive Histogram Equalization Robust Against JPEG Compression , In the 6th IAPR/IEEE International Workshop on Biometric and Forensics (IWBF), Sassari, Italy

  • M. Barni, E. Nowroozi, and B. Tondi (2017) Higher-order Adversary-Awared, Double JPEG-Detection via Selected Training on Attacked Samples , In the 25th European Signal Processing Conference (EUSIPCO), Kos, Greece

  • Google Scholar

Ph.D. Dissertation

The use of machine-learning for multimedia forensics is gaining more and more consensus, especially due to the amazing possibilities offered by modern machine learning techniques. By exploiting deep learning tools, new approaches have been proposed whose performance remarkably exceed those achieved by state-of-the-art methods based on standard machine-learning and model-based techniques. However, the inherent vulnerability and fragility of machine learning architectures pose new serious security threats, hindering the use of these tools in security-oriented applications, and, among them, multimedia forensics. The analysis of the security of machine learning-based techniques in the presence of an adversary attempting to impede the forensic analysis, and the development of new solutions capable to improve the security of such techniques is then of primary importance, and, recently, has marked the birth of a new discipline, named Adversarial Machine Learning. By focusing on Image Forensics and image manipulation detection in particular, my Ph.D. thesis contributes to the above mission by developing novel techniques for enhancing the security of binary manipulation detectors based on machine learning in several adversarial scenarios. The validity of the proposed solutions has been assessed by considering several manipulation tasks, ranging from the detection of double compression and contrast adjustment, to the detection of geometric transformations and filtering operations.

When you reach the end of what you should know, you will be at the beginning of what you should sense - - Kahlil Gibran
Ehsan Nowroozi (2020). Machine Learning Techniques for Image Forensics in Adversarial Setting. (Doctoral dissertation). Retrieved from Some Online Repository. (https://theses.eurasip.org/theses/859/machine-learning-techniques-for-image-forensics/)

  Read More