Shahnewaz Sakib

Shahnewaz Sakib

Researcher in AI safety & privacy‑preserving ML – turning theory into practice

👋 Hello and welcome to my website!

My name is Shahnewaz Sakib and I am an Assistant Professor in the Department of Computer Science and Engineering at the University of Tennessee at Chattanooga.

Here’s a quick look at what I do and what I am passionate about:

  • 🧠 Trustworthy AI – Designing systems you can understand and rely on
  • 🔐 Privacy-Preserving Machine Learning – Securing data through differential privacy & federated learning
  • ⚖️ Fairness in Algorithms – Mitigating bias in AI decision-making
  • 💬 Explainable AI – Making black-box models transparent and interpretable
  • 🛡️ AI Safety & Robustness – Defending against adversarial and unethical model behavior

🧪 Research Interests

  • AI Safety & Trustworthy AI
  • Privacy-Preserving Machine Learning
  • Privacy-Enhancing Technologies
  • Federated Learning
  • Fairness in Machine Learning
  • Explainable & Interpretable AI
  • Adversarial Robustness

🧑‍🏫 Teaching

I teach courses such as Advanced Database & Security, Advanced Topics in AI, and Biometrics & Cryptography, with a focus on hands-on, research-driven learning. See more on my Teaching page.

🗞️ Recent Highlights

  • July 2025: Our paper “Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities” was accepted to the CVAMD Workshop at ICCV 2025
  • June 2025: Selected to serve as Technical Program Committee Chair for the IEEE DISTILL 2025 Workshop, co-located with IEEE TPS 2025
  • May 2025: Awarded Ruth S. Holmberg Grant for the project titled Empowering the Next Generation of AI Security Leaders through Hands-on Research, Outreach, and Scalable Educational Models
  • March 2025: Our paper “Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models” was accepted to the TrustNLP Workshop at NAACL 2025
  • Dec 2024: The paper “Information Leakage Measures for Imperfect Statistical Information: Application to Non-Bayesian Framework” was accepted in IEEE Transactions on Information Forensics and Security
  • Oct 2024: Received acceptance for our paper “Challenging Fairness: A Comprehensive Exploration of Bias in LLM-Based Recommendations” at the 2024 IEEE International Conference on Big Data

🤝 Collaboration Opportunities
I am always happy to connect with fellow researchers, students, or industry collaborators interested in advancing responsible AI. Whether it’s about research partnerships, mentoring opportunities, or just exchanging ideas, feel free to reach out.