Researcher at the intersection of Visual Place Recognition, Novel View Synthesis, Generative Models for Vision, and Machine Learning Security.
I am a MS student in Computer Science at Fordham University and a Graduate Assistant at Dept. of Computer and Information Science. My research sits at the intersection of visual place recognition, novel view synthesis, generative models for vision, and machine learning security.
Currently I am working on hallucination-aware multi-view fusion for Visual Place Recognition (under review at Information Fusion), synthetic novel-view augmentation for VPR (under review at Pattern Recognition Letters), and membership privacy auditing in federated learning via membership inference attacks with DP-SGD defenses (under review at ACM TAISAP).
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.
Developing hallucination-aware view augmentation pipelines and evaluating how synthetic novel views affect VPR retrieval under viewpoint and appearance shift.
Applying foundation models and diffusion-based inpainting to 3D scene understanding — with a focus on detecting and filtering hallucinated regions in synthesized views.
Auditing privacy leakage in federated learning via membership inference attacks and differential privacy defenses (DP-SGD / Opacus) across medical datasets.
→ Full list on Google Scholar · Download CV ↓
I am open to research collaborations, PhD opportunities, and conversations about ML, privacy, and computer vision. Feel free to reach out.