Publications — Nafiz Sadman

Citations · live

synced 2026-05-12

h-index

i10-index

1st-auth papers

all XAI VLM cybersecurity comp-bio biometrics tools visualization showing 5 · plus 8 earlier papers on Scholar ↗

2026

1 paper

DepthPulse+: A Depth and Vital Sign Based Method for Face Presentation Attack Detection

IEEE ICC'26

Nafiz Sadman, Furkan Alaca, Farhana Zulkernine · IEEE International Conference on Communications — CISS Track

Abstract

Combines depth maps and remote photoplethysmography (rPPG) signals to detect face presentation attacks (print, replay, mask) on commodity cameras. Improves accuracy under cross-device evaluation.

2025

3 papers

Interpreting Biomedical VLMs on High-Imbalance Out-of-Distributions: An Insight into BiomedCLIP on Radiology

BioKDD'25

Nafiz Sadman, Farhana Zulkernine, Benjamin Kwan · 24th International Workshop on Data Mining in Bioinformatics

Abstract

Probes BiomedCLIP behaviour on imbalanced out-of-distribution radiology data, uses GradCAM-based interpretability to surface failure modes, and proposes evaluation harnesses for clinical robustness.

Visualizing Temporal Interval Hierarchies

NFM'25

Nafiz Sadman, Niklas Kienersi, Sean Kauffman · 17th NASA Formal Methods Symposium

Abstract

A visualization research tool for streaming data from PID controllers — Python Socket IO + D3, exposes temporal interval hierarchies for live formal-methods analysis.

Diagnosis and management of Alzheimer's disease in primary care: a real-world study in Ontario, Canada

JPCCH

(Pfizer team), Nafiz Sadman, (et al.) · Journal of Primary Care and Community Health

Abstract

Real-world Ontario EHR study of Alzheimer's diagnosis & management pathways. My contribution: EHR extraction, k-means clustering, logistic regression.

2023

1 paper

Vulnerability of Open-source Face Recognition Systems to Blackbox Attacks: A Case Study with InsightFace

IEEE CICS

Nafiz Sadman, K. A. Hasan, E. Rashno, F. Alaca, Y. Tian, F. Zulkernine · IEEE Symposium on Computational Intelligence in Cyber Security

Abstract

Blackbox attack case study on InsightFace, showing transferability of perturbations across open-source face recognition systems.

Earlier · 2019 – 2022

8 additional first-authored papers across KDD · ICML · ICMLA · SSCI · ICSOFT · ICSEA · CCWC

Earlier work — ML for HR analytics, stylometric authorship attribution, deep RL recommender systems, and speech recognition. Full list with PDFs on Google Scholar ↗.