
Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 38th cycle (2022-2025)
Department of Control and Computer Engineering (DAUIN)
Research Assistant
Department of Control and Computer Engineering (DAUIN)
Profile
PhD
Research topic
Data Privacy and Security in Federated Learning: Attacks and Defense Mechanisms
Tutors
Research presentation
Research interests
Biography
My research focuses on Data Privacy and Security in Federated Learning (FL), particularly the vulnerabilities and defenses within this privacy-preserving machine learning paradigm. Federated Learning enables decentralized model training across multiple clients without transferring raw data, addressing significant privacy concerns in data-driven applications. However, FL faces serious security risks, including gradient leakage attacks, where private data can be reconstructed from shared gradients, exposing sensitive information.
In my work, I explore how attackers might exploit gradients and initial model weights to reconstruct original private data and examine strategies to mitigate these threats. This includes developing R-CONV, a novel method that tackles data reconstruction from convolutional layers, and creating a secure, verifiable aggregation protocol for FL. These solutions are designed to counteract multiple types of attacks, striving to achieve a balance between privacy, security, and computational efficiency in federated systems. My research aims to provide robust protections to support the privacy needs of modern, distributed AI models, addressing both current and emerging challenges in federated learning security.
Research
Research groups
Publications
Latest publications View all publications in Porto@Iris
- AHMED ELTARAS, Tamer; Malluhi, Qutaibah; Savino, Alessandro; DI CARLO, Stefano; Qayyum, ... (In stampa)
R-CONV: An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients. In: WISE 2024, 2-5 December 2024
Contributo in Atti di Convegno (Proceeding) - Eltaras, Tamer Ahmed; Malluhi, Qutaibah; Savino, Alessandro; Di Carlo, Stefano; Qayyum, ... (2024)
R-CONV: An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients. In: 25th International Conference on Web Information Systems Engineering, WISE 2024, Doha (QAT), December 2–5, 2024, pp. 271-285. ISSN 0302-9743. ISBN: 9789819605750
Contributo in Atti di Convegno (Proceeding) - F., Sabry; AHMED ELTARAS, Tamer; W., Labda; F., Hamza; K., Alzoubi; Q., Malluhi (2022)
Towards On-Device Dehydration Monitoring Using Machine Learning from Wearable Device’s Data. In: SENSORS, vol. 22. ISSN 1424-8220
Contributo su Rivista - Sabry, Farida; Eltaras, Tamer; Labda, Wadha; Alzoubi, Khawla; Malluhi, Qutaibah (2022)
Machine Learning for Healthcare Wearable Devices: The Big Picture. In: JOURNAL OF HEALTHCARE ENGINEERING, vol. 2022, pp. 1-25. ISSN 2040-2309
Contributo su Rivista - AHMED ELTARAS, Tamer; Fornaciari, William; Zoni, Davide (2019)
Partial Packet Forwarding to Improve Performance in Fully Adaptive Routing for Cache-Coherent NoCs. In: 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), Pavia (ITA), 13-15 February 2019, pp. 33-40. ISBN: 978-1-7281-1644-0
Contributo in Atti di Convegno (Proceeding)