Adil Nawaz, Ph.D. — Privacy-Preserving Machine Learning

Privacy-Preserving & Federated Machine Learning

Ph.D. Graduate · Postdoctoral & Research Positions · Open to Collaboration

I received my Ph.D. in Computer Science & Technology from Shenzhen University. My research focuses on trustworthy AI, privacy-preserving and federated learning, and Bayesian optimization, with an emphasis on scalable and theoretically grounded distributed models.

I am actively seeking postdoctoral or research positions and welcome academic or industrial collaborations in federated learning, decentralized optimization, and probabilistic modeling.

Research Interests

My research focuses on developing theoretically grounded and scalable learning algorithms for distributed environments where data privacy, communication constraints, and system heterogeneity are fundamental challenges. I am particularly interested in probabilistic modeling and optimization methods that enable trustworthy and decentralized AI systems.

Core Research Directions

Privacy-Preserving ML Read more
Designing learning algorithms that guarantee formal privacy protection (e.g., differential privacy, MPC, homomorphic encryption) while maintaining model utility.
Federated Learning Read more
Training models across multiple clients without sharing raw data under communication and privacy constraints.
Bayesian Optimization Read more
Sample-efficient optimization of expensive black-box functions using probabilistic surrogate models.
Gaussian Processes Read more
Non-parametric Bayesian models defined by a mean function and kernel covariance. They provide principled uncertainty estimation and closed-form posterior inference under Gaussian assumptions.
Secure & Distributed Optimization Read more
Optimization methods (e.g., ADMM, decentralized consensus) adapted to secure and privacy-aware settings, enabling collaborative learning across untrusted or heterogeneous participants.

Application Domains

Biomedical & Healthcare AI Read more
Privacy-sensitive modeling of medical and health-related data across institutions, where data sharing is restricted by legal and ethical constraints.
Distributed Data-Centric Systems Read more
Learning from geographically distributed and statistically heterogeneous data sources with limited communication budgets.
Heterogeneous Data & Heterogeneous Resources Read more
Designing adaptive algorithms that account for varying compute, bandwidth, and data quality across clients.
Protocol-Driven & Trustworthy AI Systems Read more
Integrating learning algorithms with cryptographic and system-level protocols to ensure robustness, privacy, and reliability.

Educational Background

Ph.D., Computer Science & Technology
Shenzhen University (2021–2025)
Federated Bayesian Optimization based on Secure Gaussian Processes
M.Eng., Information & Communications Engineering
South China University of Technology (2018–2020)
Multilingual Scene Text Detection and Recognition based on Convolutional Neural Networks/em>

B.Sc., Telecommunication Engineering
University of Engineering & Technology, Peshawar (2010–2014)
Graduated with First Class Honors

Awards & Honors

2018 — Chinese Government Scholarship (CGS) Silk Road Program (awarded for M.Eng. at South China University of Technology)

2020 — Southeast University Presedential Scholarship and Nanjing Government Scholarship Award (For study at Southeast University PhD program)

2021 — Shenzhen University LiYuan Scholarship (PhD funding for 4 years in Computer Science & Technology)

2021 — Guangdong Government Outstanding International Student Scholarship & Shenzhen University Scholarship

2022 — Best Paper Finalist Award (Best Paper Finalist at the 2023 IEEE International Conference on Development and Learning, ICDL)

2023 — Excellence Award, Guangdong-Hong Kong-Macao Greater Bay Area Data Application Innovation Competition

2024 — Guangdong Government Outstanding International Student Scholarship & Shenzhen University Scholarship

2024 — Shenzhen University Outstanding Innovative Talent Scholarship (Special Prize), ¥77,000 — selected as one of the top PhD students for outstanding research achievements and innovation

2024 — AAAI Travel Scholarship Award — travel funding for attending the 38th Annual AAAI Conference on Artificial Intelligence (Vancouver, B.C., Canada)

2025 — Defended PhD Thesis

2025 — Graduated with PhD in Computer Science and Technology Ranked 3rd among all the candidates

References & Learning Materials

The following books, surveys, and seminal papers form the theoretical and methodological foundations of my research.

Dwork & Roth. The Algorithmic Foundations of Differential Privacy
PDF

McMahan et al. Communication-Efficient Learning of Deep Networks from Decentralized Data
arXiv

Kairouz et al. Advances and Open Problems in Federated Learning
arXiv

Liu et al. Recent advances on federated learning: A systematic survey
Neurocomputing Journal

Rasmussen & Williams. Gaussian Processes for Machine Learning
Book Website

Shahriari et al. Taking the Human Out of the Loop: A Review of Bayesian Optimization
PDF

Wang et al. Recent Advances in Bayesian Optimization
ACM Computing Surveys

Publications

Contact & Collaboration

I am interested in postdoctoral positions, research roles, and collaborations related to federated learning, privacy-preserving AI, and Bayesian methods.

Email: adilnawazin@gmail.com
Alternative Email:adilnawaz@email.szu.edu.cn
GitHub: SZU-AI4H
Google Scholar: Profile