Behrooz Razeghi   

Biography

Dr. Behrooz Razeghi is a postdoctoral researcher in the Biometric Security & Privacy group at the Idiap Research Institute. He completed his Ph.D. in Computer Science at the University of Geneva in 2022, where he contributed to the Stochastic Information Processing group.

During his academic journey, Dr. Razeghi gained experience as a visiting research fellow at Harvard University and as a visiting research scholar at Imperial College London. Prior to his Ph.D., he obtained an M.Sc. in Mathematics (Numerical Analysis) from Iran University of Science and Technology in 2017 and an M.Sc. in Electrical Engineering (Communications Systems) from Ferdowsi University of Mashhad in 2014.

Research Interests

Dr. Razeghi's research interests encompass the application of mathematical and statistical theories to various fields, including signal processing, machine learning, data privacy, communications, and networking. His diverse educational background has equipped him with the skills needed to address challenges in these areas.

Teaching

He was teaching assistant for:

  • Éléments de la theorie de l'information (Elements of Information Theory) - a bachelor's course (in French)
  • Structures de données (Data Structure) - a bachelor's course (in French)
  • Multiuser Information Theory and Wireless Communications - a master's course (in English)

Publications

An (almost) up-to-date list of his publications can be found on Google Scholar

The list below highlights the publications to which Behrooz Razeghi has contributed within the SIP group

  • B. Razeghi, S. Voloshynovskiy, D. Kostadinov, and O. Taran, "Privacy Preserving Identification Using Sparse Approximation with Ambiguization," in Proc. IEEE International Workshop on Information Forensics and Security (WIFS), Rennes, France, 2017, pp. 1-6. [pdf|bib]
  • D. Kostadinov, B. Razeghi, S.Voloshynovskiy, and S.Ferdowsi, "Learning Discrimination Specific, Self-Collaborative and Nonlinear Model," in Proc. IEEE Internacial Conference on Big Knowlage (ICBK), Singapore, 2018. [pdf|bib]
  • B. Razeghi, S. Voloshynovskiy, S. Ferdowsi, and D. Kostadinov, "Privacy-Preserving Identification via Layered Sparse Code Design: Distributed Servers and Multiple Access Authorization," in Proc. 26th European Signal Processing Conference (EUSIPCO), Rome, Italy, 2018. [pdf|bib]
  • B. Razeghi and S. Voloshynovskiy, "Privacy-Preserving Outsourced Media Search Using Secure Sparse Ternary Codes," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, 2018. [pdf|bib]
  • B. Razeghi, T. Stanko, B. Škoric´, and S. Voloshynovskiy, "Single-Component Privacy Guarantees in Helper Data Systems and Sparse Coding with Ambiguation," in Proc. IEEE International Workshop on Information Forensics and Security (WIFS), Delft, Netherlands, 2019. [pdf|bib]
  • S. Rezaeifar, B. Razeghi, O. Taran, T. Holotyak, and S. Voloshynovskiy, "Reconstruction of privacy-sensitive data from protected templates," in Proc. IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019. [pdf|bib]
  • D. Kostadinov, B. Razeghi, S. Rezaeifar, and S. Voloshynovskiy, "Supervised Joint Nonlinear Transform Learning with Discriminative-Ambiguous Prior for Generic Privacy-Preserved Features," in Proc. 53rd Annual Conference on Information Systems & Sciencese (CISS), Maryland, USA, 2019. [pdf|bib]
  • M. Gheisari, T. Furon, L. Amsaleg, B. Razeghi, and S. Voloshynovskiy, "Aggregation and Embedding for Group Membership Verification," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019. [pdf|bib]
  • B. Razeghi, F. P. Calmon, D. Gündüz, and S. Voloshynovskiy, "On Perfect Obfuscation: Local Information Geometry Analysis," in Proc. IEEE International Workshop on Information Forensics and Security (WIFS), New York, US, 2020. [pdf|bib]
  • S. Rezaeifar, M. Diephuis, B. Razeghi, O. Taran, D. Ullmann, and S. Voloshynovskiy, "Distributed Semi-Private Image Classification Based on Information-Bottleneck Principle," in Proc. 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, 2020. [pdf|bib]
  • S. Ferdowsi, B. Razeghi, T. Holotyak, F. P. Calmon, and S. Voloshynovskiy, "Privacy-Preserving Image Sharing via Sparsifying Layers on Convolutional Groups," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. [pdf|bib]
  • B. Razeghi, S. Ferdowsi, D. Kostadinov, F. P. Calmon, and S. Voloshynovskiy, "Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Ontario, Canada, 2021. [pdf|bib]
  • A. A. Atashin, B. Razeghi, D. Gündüz, and S. Voloshynovskiy, "Variational Leakage: The Role of Information Complexity in Privacy Leakage," in Proc. Proceedings of the 3rd ACM Workshop on Wireless Security and Machine Learning, 2021, pp. 91-96. [pdf|bib]
  • I. Shiri, M. Amini, Y. Salimi, A. Sanaat, A. Saberi, B. Razeghi, S. Ferdowsi, A. V. Sadr, S. Voloshynovskiy, D. Gündüz, A. Rahmim, and H. Zaidi, "Multi-Institutional PET/CT Image Segmentation Using a Decentralized Federated Deep Transformer Learning Algorithm," Journal of Nuclear Medicine, vol. 63, iss. supplement 2, pp. 3348-3348, 2022. [link|bib]
  • I. Shiri, A. V. Sadr, M. Amini, Y. Salimi, A. Sanaat, A. Akhavanallaf, B. Razeghi, S. Ferdowsi, A. Saberi, H. Arabi, and others, "Decentralized distributed multi-institutional PET image segmentation using a federated deep learning framework," Clinical Nuclear Medicine, vol. 47, iss. 7, pp. 606-617, 2022. [pdf|bib]
  • I. Shiri, E. Showkatian, R. Mohammadi, B. Razeghi, S. Bagheri, G. Hajianfar, Y. Salimi, M. Amini, M. Ghelich Oghli, S. Ferdowsi, S. Voloshynovskiy, and H. Zaidi, "Collaborative Multi-Institutional Prostate Lesion Segmentation from MR images Using Deep Federated Learning Framework," in Proc. IEEE Nuclear Science Symposium, Medical Imaging Conference, 2022. [pdf|bib]
  • B. Razeghi, S. Rezaeifar, S. Ferdowsi, T. Holotyak, and S. Voloshynovskiy, "Compressed Data Sharing based on Information Bottleneck Model," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. [pdf|bib]
  • I. Shiri, Y. Salimi, M. Maghsudi, E. Jenabi, S. Harsini, B. Razeghi, S. Mostafaei, G. Hajianfar, A. Sanaat, E. Jafari, and others, "Differential privacy preserved federated transfer learning for multi-institutional 68Ga-PET image artefact detection and disentanglement," European Journal of Nuclear Medicine and Molecular Imaging (EJNMMI), pp. 1-14, 2023. [pdf|bib]
  • B. Razeghi, F. P. Calmon, D. Gündüz, and S. Voloshynovskiy, "Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility," IEEE Transactions on Information Forensics and Security (TIFS), 2023. [pdf|bib]
  • I. Shiri, B. Razeghi, A. Vafaei Sadr, M. Amini, Y. Salimi, S. Ferdowsi, P. Boor, D. Gündüz, S. Voloshynovskiy, and H. Zaidi, "Multi-Institutional PET/CT Image Segmentation Using Federated Deep Transformer Learning," Computer methods and programs in biomedicine, vol. 240, 2023. [pdf|bib]
  • I. Shiri, A. Vafaei Sadr, A. Akhavan, Y. Salimi, A. Sanaat, M. Amini, B. Razeghi, A. Saberi, H. Arabi, S. Ferdowsi, and others, "Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning," European Journal of Nuclear Medicine and Molecular Imaging, vol. 50, iss. 4, pp. 1034-1050, 2023. [pdf|bib]
  • I. Shiri, Y. Salimi, N. Sirjani, B. Razeghi, S. Bagherieh, M. Pakbin, Z. Mansouri, G. Hajianfar, A. H. Avval, D. Askari, and others, "Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset," Medical Physics, 2024. [pdf|bib]
  • B. Razeghi, M. Gheisari, A. Atashin, D. Kostadinov, S. Marcel, D. Gunduz, and S. Voloshynovskiy, "Group Membership Verification via Nonlinear Sparsifying Transform Learning," IEEE Access, vol. 12, pp. 86739-86751, 2024. [pdf|bib]
  • I. Shiri, B. Razeghi, S. Ferdowsi, Y. Salimi, D. Gündüz, D. Teodoro, S. Voloshynovskiy, and H. Zaidi, "PRIMIS: Privacy-preserving medical image sharing via deep sparsifying transform learning with obfuscation," Journal of biomedical informatics, vol. 150, 2024. [pdf|bib]