/ About
I research security and privacy of machine learning, with a focus on federated learning under realistic constraints — heterogeneous clients, poisoning and inference threats, and the trade-offs between accuracy, privacy, and robustness. I like to work where theory, systems, and experimentation meet, and I keep an engineering background in IoT and distributed platforms from earlier international collaborations.
/ Research interests
Federated Learning Robustness
Behavior under non-IID clients, lightweight architectures, and adversarial participants.
Privacy Leakage
Membership inference under temporal and system-level settings — realistic threat models.
Poisoning & Backdoors
Data and model poisoning, evaluation of defenses beyond worst-case assumptions.
Privacy-Preserving ML
Differential privacy, secure aggregation, and auditing protocols for FL pipelines.
/ Education
/ Toolbox
/ Latest writing
Week 12: Dynamic Allocation — Solution
· Basis and Practice in Programming_DASF004_41, Solutions
Week 12: Dynamic Allocation
· Basis and Practice in Programming_DASF004_41, Exercices
Week 11: Strings and String Functions — Solution
· Basis and Practice in Programming_DASF004_41, Solutions
Week 11: Strings and String Functions
· Basis and Practice in Programming_DASF004_41, Exercices
/ Get in touch
Open to research collaborations, PhD opportunities, and ML/AI engineering roles in trustworthy and privacy-aware AI. Reach me at abdenour@g.skku.edu.