Cybersecurity & AI Research

Shuvodip
Biswas

MASc. Candidate · Concordia University

Aspiring cybersecurity professional with academic training in computer science and information systems security. Completed a B.Sc. in Computer Science at North South University in 2024 and currently pursuing an MASc. at Concordia University. Brings hands-on experience in building web applications, mentoring students, and applying secure development practices to real-world problems.

profile.sh
$ whoami
shuvodip_biswas

$ cat ./info.json
"role": "Graduate Researcher"
"institution": "Concordia University"
"focus": "Cybersecurity + AI/ML"
"papers": 2
"students_mentored": 100+

$ ls ./skills/
deep-learning/ explainableAI/
secure-dev/ data-analysis/

$
Background & Overview

I am an aspiring cybersecurity professional with a strong foundation in computer science and information systems security. I completed my B.Sc. in Computer Science at North South University in 2024, graduating with a research background in explainable AI and deep learning applied to healthcare.

I am currently pursuing an MASc. at Concordia University, where my research focuses on the intersection of cybersecurity and machine learning. I am interested in building trustworthy, interpretable AI systems and understanding how adversarial threats affect modern ML pipelines.

Beyond research, I enjoy mentoring students and translating complex technical concepts into accessible learning experiences—skills honed over two years as a Teaching Assistant at NSU.

2+
Research Papers
100+
Students Mentored
4+
Years Teaching
3
Industry Roles
Technical Expertise
🔐

Cybersecurity

Secure Dev InfoSec Threat Modeling Cryptography
🧠

AI / Machine Learning

TensorFlow PyTorch Keras Explainable AI Deep Learning
💻

Programming

Python Java C/C++ SQL React HTML/CSS
📊

Data Analysis

Pandas NumPy SciPy Matplotlib Tableau
🔬

Research Methods

SHAP GRAD-CAM LRP LIME SSL
🌐

Web Development

Responsive Design REST APIs Cross-browser Compat.
Work & Academic History
2025 – Present Current
Graduate Research Assistant
Concordia University — Montréal, QC
  • Conducting research at the intersection of cybersecurity and machine learning under faculty supervision.
  • Investigating adversarial robustness, secure ML pipelines, and trustworthy AI systems.
  • Contributing to lab publications and presenting findings in seminars and group meetings.
  • Collaborating with cross-disciplinary team members on grant-funded research projects.
July 2024 – December 2025 Academic
Lab Instructor
North South University — Dhaka, Bangladesh
  • Designed and delivered lectures on Java programming and database management to undergraduate students.
  • Developed projects focusing on OOP, database design, and efficient algorithms.
  • Mentored students on semester-long projects, resulting in successful completion and presentations.
July 2024 – August 2025 Industry
Web Developer
Green World Machinery
  • Designed, developed, and maintained responsive websites and web applications.
  • Built reusable, scalable, and efficient code using HTML, CSS, JavaScript, and modern frameworks.
  • Optimized websites for speed, scalability, and cross-browser compatibility.
June 2022 – June 2024 Academic
Teaching Assistant
North South University — Dhaka, Bangladesh
  • Guided 100+ students in Statistics, improving average performance by 15%.
  • Covered probability theory, statistical inference, and hypothesis testing.
  • Assisted in preparing course materials, grading, and additional tutoring sessions.
June 2023 – October 2023 Internship
Virtual Intern — Data Analysis
eSRD Lab, BUET
  • Completed 40+ hours of intensive data analysis training.
  • Analyzed e-commerce datasets, providing insights with potential 10% sales improvement.
  • Gained proficiency in multidimensional modeling, data pre-processing, and analysis frameworks.
Publications & Projects
Conference Paper Published
How Explainable Are Black-Box Models in Brain Tumor Classification?

Developed deep learning models (VGG16, VGG19) for brain MRI analysis, focusing on interpretability using SHAP, LRP, GRAD-CAM, and LIME. Improved transparency and trust in AI-based diagnostic decisions through explainable AI techniques. Collaborated with healthcare professionals to address real-world challenges in medical diagnostics.

📍 IEEE ICCIT 2024 — 27th International Conference on Computer & Information Technology
Journal Article
TabularClust: Enhancing Unsupervised Clustering with Contrastive Self-Supervised Learning and Attention-Driven Optimization

Novel architecture designed to improve embedding quality and cluster tabular data effectively using self-supervised learning (SSL). The pipeline involves feature extraction, dimensionality reduction, and embedding enhancement via SSL frameworks, enabling more accurate and interpretable clustering outcomes.

📍 Submitted — IJCNN 2026
Project Completed
Multimodal Image Disease Classification with Filter Visualization & Sparsing

Processes preprocessed multimodal data through convolutional layers for feature extraction, with final layers handling classification. Filter visualization reveals what patterns the network has learned, while sparsing improves efficiency by pruning less meaningful connections.

Get In Touch

Whether you have a research collaboration in mind, a question about my work, or just want to connect, feel free to reach out.