Research

Privacy and Robustness of Large Language Models

Privacy and Security of Machine Learning

Federated Learning

Natural Language Processing

Adversarial ML

Applied Machine Learning

• Machine Unlearning in Large Language Models.
  Collaborators: Kang Gu,  Dartmouth College
  Dr. Shagufta Mehnaz, Penn State University, USA
  
  

• Privacy and  Security  Implications of Personalized Federated Learning
  Collaborators: Dr. Shagufta Mehnaz,   Penn State University, USA
  
  

• Privacy-preserved  Energy Consumption Modeling
  Collaborators: Dr. Satadru Dey, Dr. Shagufta Mehnaz,  Penn State University, USA
  
  

1.  Kabir, Ehsanul, Zeyu Song, Md Rafi Ur Rashid, and Shagufta Mehnaz. "FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attacks."
   Accepted in 45th IEEE Symposium on Security and Privacy                 
   arXiv preprint: arxiv.org/abs/2310.1615
   
   

2. Raiaan, Mohaimenul Azam Khan, Kaniz Fatema, Inam Ullah Khan, Sami Azam, Md Rafi ur Rashid, Md Saddam Hossain Mukta, Mirjam Jonkman, and Friso De Boer. "A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images." IEEE Access (2023).

3. Md. Rafi-Ur-Rashid, Mahim Mahbub, and Muhammad Abdullah Adnan. 2022. Breaking the Curse of Class Imbalance: Bangla Text Classification. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 1, 1, Article 1 (January 2022), 21 pages.
   
   

4.  Md. Rafi Ur Rashid, Mahim Mahbub, and Muhammad Abdullah Adnan. 2021. BAND: A Benchmark Dataset for Bangla News Audio Classification. In ACM Multimedia Asia (MMAsia ’21). Association for Computing Machinery, New York, NY, USA, Article 45, 1–6.
   
   

Awarded research grant for by the Institute of Advanced Research (IAR), United International University, Bangladesh for the project: Detection  & Analysis of Common Visual Disorders from Low-Resolution Fundus Images.