ML
Fordham University · MS Computer Science

Muhammad
Zawad Mahmud

Researcher at the intersection of Privacy-Preserving Machine Learning, Computer Vision, and Applied AI — building systems that are technically rigorous and ethically grounded.

4.0
Graduate GPA MS Computer Science, Fordham University
10+
Publications Journals · IEEE Conferences · Preprints
3+
Years Teaching Experience North South University · Green University
01

About

Position MS Computer Science, Fordham University
Lab Fordham Robotics & Computer Vision Lab (FRCVLab)
Seeking PhD positions in ML / Computer Vision / Security
Email mmahmud9@fordham.edu
Background

I am a first-year MS student in Computer Science at Fordham University and a Graduate Assistant at Dept. of Computer and Information Science (RH). My research sits at the intersection of privacy-preserving machine learning, federated systems, and computer vision.

Currently I am working on membership inference attacks against federated learning models with differential privacy defenses (DP-SGD / Opacus), and on novel view synthesis for Visual Place Recognition using GenWarp and diffusion-based inpainting, submitted to IROS 2026.

Before Fordham, I was a Lab Instructor and Adjunct Lecturer at North South University and Green University of Bangladesh, where I taught and designed courses across Data Structures, DBMS, and Software Engineering.

02

Research Interests

🔒

Privacy & Security in ML

Studying membership inference attacks, shadow model training, and differential privacy (DP-SGD / Opacus) as defenses in federated learning settings.

Federated Learning MIA DP-SGD Opacus
👁️

Computer Vision

Novel view synthesis for Visual Place Recognition — analyzing how hallucinated pixels from diffusion inpainting affect recognition performance across real-world datasets.

GenWarp NeRF VPR Diffusion
🛡️

Applied ML for Security

Applying machine learning to real-world security challenges — including IoT intrusion detection, SDN-based threat detection, and resource-efficient multi-class threat classification in constrained environments.

IoT Security SDN Intrusion Detection XAI
03

Publications

2026

Systematic Evaluation of Novel View Synthesis for Video Place Recognition

International Conference on Intelligent Robots and Systems (IROS) · arXiv Preprint ↗
Submitted
2025

A Novel Clinical Dataset with XAI-Integrated Ensemble and Large Language Models for Interpretable Dengue Detection

Array, Elsevier (Q1, IF: 4.5)
Under Review
2024

Advanced Vision Transformers and Open-Set Learning for Robust Mosquito Classification: A Novel Approach to Entomological Studies

PLoS Computational Biology, vol. 20, no. 12 · DOI ↗
Published
2024

Advance Transfer Learning Approach for Identification of Multiclass Skin Disease with LIME Explainable AI Technique

27th International Conference on Computer and Information Technology (ICCIT 2024) · DOI ↗
Published
2024

Enhancing Multi-Class Disease Classification: Neoplasms, Cardiovascular, Nervous System, and Digestive Disorders Using Advanced LLMs

27th International Conference on Computer and Information Technology (ICCIT 2024) · DOI ↗
Published
2026

Privacy Leakage in Federated Learning: A Membership Inference Attack Analysis with Differential Privacy Defenses

In Preparation
Ongoing
2026

HAGVA: Hallucination-Aware Generative View Augmentation for Visual Place Recognition

In Preparation
Ongoing

→ Full list on Google Scholar

04

Experience

2025 — Present
Graduate Assistant
Dept. of Computer and Information Science (RH), Fordham University
Conducting research in generative AI and visual place recognition under Dr. Damian Lyons.
2024 — 2025
Lab Instructor · Adjunct Lecturer
North South University · Green University of Bangladesh
Designed and delivered theory and lab courses including Data Structures, DBMS, Software Engineering, and Structured Programming for undergraduate students.
2022 — 2024
Undergraduate & Graduate Teaching Assistant
Dept. of Mathematics & Physics, North South University
Assisted nine faculty members in pre-calculus, linear algebra, and calculus courses.
05

Get in Touch

I am open to research collaborations, PhD opportunities, and conversations about ML, privacy, and computer vision. Feel free to reach out.