BGK 596E Seminars

CRN 23829

  2  
Title FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System
Speaker İrem Yılmaz
Date May 16th, 2025
Time 10:30 (GMT+3)
Microsoft Teams Meeting ID:
*** *** *** **
Passcode:
******
(Please, contact the secretary's office.)
Abstract
This paper presents FedML-HE, a practical federated learning system that integrates homomorphic encryption (HE) to protect user privacy during model aggregation. By selectively encrypting sensitive model parameters, FedML-HE significantly reduces computational and communication overhead. It demonstrates strong scalability, achieving up to 10x and 40x efficiency gains for ResNet-50 and BERT models, respectively.
  1  
Title Exploring Web3 From the View of Blockchain
Speaker Nadir Alishli
Date April 18th, 2025
Time 10:30 (GMT+3)
Microsoft Teams Meeting ID:
*** *** *** **
Passcode:
******
(Please, contact the secretary's office.)
Abstract
Web3 is the most hyped concept from 2020 to date, greatly motivating the prosperity of the Internet of Value and Metaverse. However, no solid evidence stipulates the exact definition, criterion, or standard in the sense of such a buzzword. To fill the gap, we aim to clarify the term in this work. We narrow down the connotation of Web3 by separating it from high-level controversy argues and, instead, focusing on its protocol, architecture, and evaluation from the perspective of blockchain fields. Specifically, we have identified all potential architectural design types and evaluated each of them by employing the scenario-based architecture evaluation method. The evaluation shows that existing applications are neither secure nor adoptable as claimed. Meanwhile, we also discuss opportunities and challenges surrounding the Web3 space and answer several prevailing questions from communities. A primary result is that Web3 still relies on traditional internet infrastructure, not as independent as advocated. This report, as of June 2022, provides the first strict research on Web3 in the view of blockchain. We hope that this work would provide a guide for the development of future Web3 services.

 

İTÜ Informatics Institute

bilisim-anasayfa-hakkimizda

ITU Informatics Institute provides graduate-level education and research in applied informatics, computer sciences, computational science and engineering, communication systems under the following programs.

Faculty members and students conduct research supported by national and international organızatıons in the fields of electromagnetic fields, communication systems/regulations, computational materials design, computational chemistry/biology, cryptography, signal/data processing/visualization, big data management, climate and ocean sciences, 

  • List of Most Influential Scientists; Associate Professor. B. Uğur Töreyin (article by Dr. John PA Ioannidis, K. W. Boyack and J. Baas published in the journal PLOS Biology)
  • Beltus Nkwawir Wiysobunri, the best project award in the Science category, in the 2020 International Students Project Competition
  • Argenit company, of which Dr. Abdulkerim Çapar is among the founding partners, received the "National-International Supports" First Prize of ITU ARI Teknokent.
  • TÜBİTAK 2242 University Students Project Competition in Priority Areas: Istanbul region first place - Ahmet Burak Özyurt
  • Best Presentation Award at ICAT'18 Conference: Sena Efsun Cebeci, 2018
  • Tubitak Incentive Award; 2016 Assoc. Prof. Adem Tekin
  • “Technical Paper” and “Willis H. Carrier” Award by the American Heating, Cooling and Air Conditioning Association; 2016 Assist. Prof. Dr. H. Salih Erden
  • Science Heroes Association Young Scientist of the Year Award; 2016 Assoc. B. Uğur Töreyin Best Poster Award at PRACEdays 2016 conference; Samet Demir
  • ITU Most Successful Thesis Award; 2016 Hatice Gokcan

There is also a High Performance Computing Laboratory established with the support of the State Planning Organization within the Institute.