Research Interests
Software Engineering AI/ML Security Blockchain Technology LLM Systems Image Steganography Microservices Architecture Distributed SystemsResearch Projects
Securing Machine Learning Model Ecosystems: A Comprehensive Security Analysis
Conducting a comprehensive security analysis of 15 major machine learning platforms, focusing on remote code execution vulnerabilities in ML model hubs. This research builds upon foundational work treating ML models as executable code, systematically analyzing platforms like Hugging Face Hub (752,000+ models), Kaggle, TensorFlow Hub, and PyTorch Hub. Developing a security maturity framework that categorizes platforms from "Basic" to "Advanced" based on protective measures, evaluating defensive technologies like SafeTensors and MalHug framework, and contributing to ML supply chain security standards.
Collaboration: Collaborating with Mohammad Latif Siddique, Ph.D. candidate at University of Notre Dame, USA, who specializes in software engineering, software security, code generation, and applied machine learning. Currently a Ph.D. intern at Meta (Summer 2025) working with WhatsApp Core Consumer Messaging Groups & Communities on LLM applications. Initial independent research expanded to collaboration in January 2025, building upon the work of Zhao et al. (2024) on ML model security vulnerabilities.
Read MoreMaking AI Reliable: Design by Contract for Large Language Models
Developed an extended taxonomy for API contracts in LLM libraries and created a design by contract tool to enforce API contracts and simplify debugging for popular ML libraries. Conducted empirical studies on real-world issues, implemented automated contract validation, and proposed recommendations for LLM library developers and LLMOps tool builders.
Collaboration: Collaborating with Dr. Akond Rahman, Assistant Professor at Auburn University, who specializes in DevOps, cybersecurity, and secure software development. Dr. Rahman leads the PASER (Practical and Actionable Software Engineering Research) group, focusing on practical software engineering research that bridges the gap between academic research and industry practice.
Read MoreBlockchain in Healthcare 2.0
Engineered an advanced blockchain framework with sharding, Layer-2 solutions, and a DAG ledger, implementing patient-centric consent management, HL7 FHIR standards, and privacy-preserving computation.
Collaboration: Project supervised by Professor ASM Latiful Hoque from BUET (my undergraduate thesis supervisor), who specializes in data warehousing, data mining, big data analytics, and database technologies.
Read MorePublications
An Unconventional Tale on Sentiment Analysis over Anonymous Online Reporting by the People in Bangladesh during an Outburst Period
Developed Bangladesh's first anonymous online reporting system and analyzed crowd-sourced reports using transformer models and NRC Lexicon-based analysis. Initially rejected due to novelty concerns and misalignment with conference research goals. Currently working to address these issues and prepare for submission to a more suitable venue.