Research

Safety and Robustness of Large Language Models

Secure and Trustworthy Machine Learning

Privacy Preserved Machine Learning

Federated Learning

Natural Language Processing

Applied  Machine Learning

*Feel free to contact me if you are interested in doing research collaboration

1.  Rashid, Md Rafi Ur, et al. "Forget to flourish: Leveraging machine-unlearning on pretrained language models for privacy leakage." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. No. 19. 2025. 
    

2. Gu, K., Rashid, M. R. U., Sultana, N., & Mehnaz, S. (2025, June). Robust Unlearning for Large Language Models. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp. 143-155).                               

3. Hase, Ryo, Md Rafi Ur Rashid, Ashley Lewis, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, and Ye Wang.
   "Smoothed Embeddings for Robust Language Models." In Neurips Safe Generative AI Workshop 2024.                                                                   

4. Kabir, Ehsanul, Zeyu Song, Md Rafi Ur Rashid, and Shagufta Mehnaz. "FLShield: A Validation-Based Federated Learning Framework to Defend Against Poisoning Attacks.” 2024 IEEE Symposium on Security and Privacy (S&P)
   
   

5. Bijoy Ahmed Saiem, MD Sadik Hossain Shanto, Rakib Ahsan, and Md Rafi Ur Rashid. SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains. In Proceedings of  the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) (Volume 4: pages 548–579)
   
   

6. 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).

7. 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.
   
   Full publication list available on Google Scholar

• Analyzing The Security & Privacy Threats of Personalized Federated Learning
  - Current PhD project; Working as a PI  
  
  

• Secure and Private Machine Learning Applications for Autonomous Battery Electric Vehicles
  - A collaboration between Penn State Computer Science and Mechanical Eng. Departments, Working as a Co-PI
  
  

Awarded research grant 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.