Licentiate Thesis Defense-Samaneh Mohammadi

Welcome to the licentiate Thesis Defense of Samaneh Mohammadi

Licentiate Thesis Title: Balancing Privacy and Performance in Emerging Applications of Federated Learning

Time: 2023-12-14 13:15 (CET) 

Location: Room Paros of Mälardalen University (Västerås)

Supervisors: Prof. Francesco Flammini and Dr. Ali Balador


Federated Learning (FL) has emerged as a novel paradigm within machine learning (ML) that allows multiple devices to collaboratively train a shared ML model without sharing their private data with a central server. FL has gained popularity across various applications by eliminating the necessity for centralized data storage, thereby improving the confidentiality of sensitive information. 

Among the new FL applications, this thesis focuses on Speech Emotion Recognition (SER), which involves the analysis of audio signals from human speech to identify patterns and classify the conveyed emotions. When SER is implemented within a FL framework, even though speech data remains on local devices, new privacy challenges emerge during the training phase and the exchange of SER model update parameters between servers and clients. 

These challenges encompass the potential for privacy leakage and adversarial attacks, including model inversion attacks and membership or property inference attacks, which can be conducted by unauthorized or malicious parties to exploit the shared SER model, compromising client data confidentiality and revealing sensitive information.While several privacy-preserving solutions have been developed to mitigate potential breaches in FL architectures, those are too generic to be easily integrated into specific applications. Furthermore, incorporating existing privacy-preserving mechanisms into the FL framework can increase communication and computational overheads, which may, in turn, compromise data utility and learning performance.

This thesis aims to propose privacy-preserving methods in FL for emerging security-critical applications such as SER while addressing the challenges related to their effect on performance. First, we categorize and analyze recent research on privacy-preserving mechanisms in FL, with a focus on assessing their effects on FL performance and how to balance privacy and performance across various applications. Second, we design an optimized FL setup tailored to SER applications in order to evaluate effects on performance and overhead. Third, we design and develop privacy-preserving mechanisms within FL to safeguard against potential privacy threats while ensuring the confidentiality of clients’ data. Finally, we propose and evaluate new methods for FL in SER and integrate them with appropriate privacy-preserving mechanisms to achieve an optimal balance of privacy with efficiency, accuracy, as well as communication and computation overhead.

List of publication in this Thesis 

Paper A:

Title: Balancing Privacy and Performance in Federated Learning: A Systematic Literature Review on Methods and Metrics. Authors: Samaneh Mohammadi, Ali Balador, Sima Sinaei, and Francesco Flammini

Status: Submitted, Journal of Parallel and Distributed Computing – Special Issue on Secure and Efficient Distributed Computation for Emerging Systems on the edge.  

Paper B

Title: Hyperparameters Optimization for Federated Learning System: Speech Emotion Recognition Case Study.  Authors: Kateryna Mishchenko, Samaneh Mohammadi, Mohammadreza Mohammadi, and Sima Sinaei

Status: Published, The 1st International Symposium on Federated Learning Technologies and Applications (FLTA) in conjunction with The Eighth IEEE International Conference on Fog and Mobile Edge Computing (FMEC 2023).

 Paper C

Title: Balancing Privacy and Accuracy in Federated Learning for Speech  Emotion Recognition. Authors: Samaneh Mohammadi, Mohammadreza Mohammadi, Sima Sinaei, Ali Balador, Ehsan Nowroozi, Francesco Flammini, and Mauro Conti

Status: Published, 18th Conference on Computer Science and Intelligence Systems (FedCSIS 2023)

 Paper D

Title: Optimized Paillier Homomorphic Encryption in Federated Learning for Speech Emotion Recognition. Authors: Samaneh Mohammadi, Sima Sinaei, Ali Balador, and Francesco Flammini

Status: Published, IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC 2023)

 Paper E

Title: Secure and Efficient Federated Learning by Combining Homomorphic Encryption and Gradient Pruning in Speech Emotion Recognition. Authors: Samaneh Mohammadi, Sima Sinaei, Ali Balador and Francesco Flammini

Status: Published, The 18th International Conference on Information Security Practice and Experience (ISPEC 2023)

Leave a Reply

Your email address will not be published. Required fields are marked *