activity
20242026
collaborators

18 papers

cs.CR2026

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems

Md Takrim Ul Alam, Akif Islam, Mohd Ruhul Ameen +2

Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subv…

cs.HC2026

Critical Thinking in the Age of Artificial Intelligence: A Survey-Based Study with Machine Learning Insights

M Murshidul Bari, Akif Islam, Mohd Ruhul Ameen +2

The growing use of artificial intelligence (AI) in education, professional work, and everyday problem-solving has raised important questions about its effect on human reasoning. Wh…

cs.CV2026

3D MRI-Based Alzheimer's Disease Classification Using Multi-Modal 3D CNN with Leakage-Aware Subject-Level Evaluation

Md Sifat, Sania Akter, Akif Islam +5

Deep learning has become an important tool for Alzheimer's disease (AD) classification from structural MRI. Many existing studies analyze individual 2D slices extracted from MRI vo…

cs.CV2025

Multi Class Parkinson Disease Detection Based on Finger Tapping Using Attention Enhanced CNN BiLSTM

Abu Saleh Musa Miah, Najmul Hassan, Md Maruf Al Hossain +2

Accurate evaluation of Parkinsons disease (PD) severity is essential for effective clinical management and intervention development. Despite the proposal of several gesture based P…

cs.CV2025

Stack Transformer Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition

Koki Hirooka, Abu Saleh Musa Miah, Tatsuya Murakami +3

Hand gesture-based Sign Language Recognition (SLR) serves as a crucial communication bridge between deaf and non-deaf individuals. While Graph Convolutional Networks (GCNs) are com…

cs.CV2025

Oitijjo-3D: Generative AI Framework for Rapid 3D Heritage Reconstruction from Street View Imagery

Momen Khandoker Ope, Akif Islam, Mohd Ruhul Ameen +3

Cultural heritage restoration in Bangladesh faces a dual challenge of limited resources and scarce technical expertise. Traditional 3D digitization methods, such as photogrammetry…