- EncCluster: Scalable Functional Encryption in Federated Learning through Weight Clustering and Probabilistic Filters, Pervasive and Mobile Computing Journal, 2025.
- Bringing Functional Encryption in Federated Foundational Models, NeurIPS 2024 Workshop on Federated Foundation Models.
- Balancing Privacy and Performance in Federated Learning: A Systematic Literature Review on Methods and Metrics, Journal of Parallel and Distributed Computing, 2024.
- Secure and Efficient Federated Learning by Combining Homomorphic Encryption and Gradient Pruning in Speech Emotion Recognition, ISPEC 2023.
- Balancing Privacy and Accuracy Federated Learning for Speech Emotion Recognition, FedCSIS 2023 (Best Paper Award).
- Hyperparameters optimization for federated learning system: Speech emotion recognition case study, FMEC 2023.
- Optimized paillier homomorphic encryption in federated learning for speech emotion recognition, IEEE COMPSAC 2023.
Research Experience
- Researcher at RISE Research Institute of Sweden
- Experience at the University of Tehran
- Work experience at Openinside Co.
- Actively involved in two major European research projects: DADAP Project (developing an AI model for mental health disorders using federated learning) and DAIS Project (applying privacy-preserving techniques in federated learning for industrial use-cases)
Education
- PhD: Mälardalen University
- MSc: Tehran University
Background
- Industrial PhD candidate with over five years of experience in AI and privacy-preserving machine learning
- Research interests include distributed machine learning, federated learning, AI privacy, and edge AI
- Focuses on scalable, secure, and efficient ML models for real-world distributed systems