Samaneh Mohammadi
Forsknings- och utvecklingsingenjör
Email
Location
Västerås
ORCID
Samaneh Mohammad joined RISE SICS as a Ph.D. candidate in Distributed Artificial Intelligence in 2021. Her research interests include machine learning, distributed and efficient ML, privacy and security, federated learning, and edge artificial intelligence. She focuses on developing privacy-preserving and efficient AI models, particularly in decentralized and edge computing environments.
She has been involved in two major European projects:
- DADAP Project (ibima.eu/es/dadap): Developing an AI model for mental health disorders and utilizing federated learning to enable on-site AI-based psychiatric diagnostics while ensuring privacy through personalized differential privacy.
- DAIS Project (dais-project.eu): Working on privacy-preserving techniques (differential privacy, homomorphic, and functional encryption) in federated learning for industrial applications, focusing on balancing privacy and performance.
She received her master's degree in Information Technology Engineering from the University of Tehran in 2020. Her thesis focused on "Anomaly Detection in Dynamic Networks" using deep learning and inductive learning.
Feel free to visit her LinkedIn https://www.linkedin.com/in/samaneh-mohammadi-22879b159/
Ask me about
Publications
Ask me about
Publications
- EncCluster : Scalable functional encryption in federated learning through weigh…
- Empirical Analysis of Asynchronous Federated Learning on Heterogeneous Devices …
- Balancing privacy and performance in federated learning : A systematic literatu…
- Optimized Paillier Homomorphic Encryption in Federated Learning for Speech Emot…
- Hyperparameters Optimization for Federated Learning System : Speech Emotion Rec…
- Balancing Privacy and Accuracy in Federated Learning for Speech Emotion Recogni…
- Secure and Efficient Federated Learning by Combining Homomorphic Encryption and…