Research
Publications
Papers, preprints, and ongoing work, organized by year and research topic.
2026
DAMM: Dynamic Modality Aware Weighted Embeddings Fusion for Multimodal Meme Detection
Do Vision–Language Models Trust Incorrect Anomaly Regions? A Counterfactual Reliability Study for Industrial Inspection
Under Review
2024
On Utilizing Deep Learning Models for Preventing Harmful Response in LLMs
Under Review
Abstract
Past few years have witnessed tremendous progress in artificial intelligence (AI) technologies including but not limited to natural language processing (NLP), metaverse, and generative models. To enhance the security of LLMs and prevent them from responding to adversarial prompts, we utilize machine learning, deep learning and transformer models as external prompt classifiers. Our proposed ensemble of the BERT-DistilBERT model achieved 97.56% accuracy in identifying malicious/adversarial prompts.
Air Quality Monitoring Using Statistical Learning Models for Sustainable Environment
Parametric Optimization and Comparative Study of Machine Learning and Deep Learning Algorithms for Breast Cancer Diagnosis
Assessing AI Chatbot Responses in Promoting COVID-19 Vaccine Acceptance
Adversarial Learning of Security Risk in Cobots Driven Industry
Accepted
Applications of Multimodal Deep Learning in Medicine
Under Review
Enhancing BERT-Based Models for Detecting Race, Violence, and Hate Speech in Low-Resource Settings
Under Review
Building Blockchain-powered Decentralized Applications with Solidity: A Project-Oriented Guide
In Progress