Graduate Research Assistant
National University of Sciences and Technology (NUST)
Conducted breakthrough research in Byzantine-robust federated learning and privacy-preserving ML, producing two papers under peer review.
Key Achievements
- Designed A3 aggregation algorithm achieving 94.99% accuracy with only 0.71% variance across 5 Byzantine attack types
- Outperformed state-of-the-art: TrimmedMean (2.62% variance), Multikrum (54% variance)
- Conducted systematic review analyzing 100+ federated learning papers (2022-2025)
- Validated on CIC-IDS2017 dataset with 2.8M network flow records