Air Quality Prediction Model for Monitoring AQI Aritra Das, Himanshu Gupta EPJ Web of Conferences, 2025 Air pollution causes major concerns to human health and the environment. Accurately estimating the Air Quality Index (AQI) is vital for proactive policymaking, health warnings, and urban planning. This research proposes a complete framework that incorporates deep learning models—specifically Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) networks—with ensemble learning methods, particularly Extreme Gradient Boosting (XGBoost), to predict AQI. Our technique harnesses the capabilities of deep neural networks to capture complex nonlinear correlations from high-dimensional environmental data, while ensemble approaches enhance predictions by effectively handling feature interactions and missing data. Extensive data collection from urban monitoring stations, rigorous preprocessing, and detailed model design are carried out. Experimental findings suggest that the hybrid model outperforms standalone deep learning or ensemble methods, resulting in higher R² scores and lower error metrics. The study also discusses real-time applications, integration with additional data sources, and future research directions in AQI forecasting, aiming to support dynamic and accurate environmental monitoring systems.
Harnessing Transfer Learning for Rapid Malware Family Classification in Large-Scale Cyber Datasets Rishabh Mohan, Himanshu Gupta EPJ Web of Conferences, 2025 Malware classification remains a critical challenge in cybersecurity, particularly in an era of rapidly evolving threats and vast datasets. Traditional machine learning methods struggle to keep pace with the diversity and volume of malware samples. This paper explores the application of transfer learning to classify malware families efficiently in large-scale cyber datasets. Leveraging pre-trained deep learning models, we demonstrate significant improvements in classification accuracy and speed while reducing the dependency on extensive labelled data. By utilizing pre-trained architectures such as Convolutional Neural Networks (CNNs) and Transformers, we exploit their ability to learn transferable features, minimizing the need for domain-specific knowledge. Furthermore, our methodology incorporates fine-tuning and domain adaptation techniques to ensure relevance and robustness in malware classification tasks. We conduct extensive experiments using real-world malware datasets, showcasing that transfer learning not only reduces computational overhead but also achieves superior performance compared to traditional approaches. Our results demonstrate the efficacy of this approach in handling skewed data sets, preventing overfitting, and enabling rapid deployment in dynamic cyber spaces. Our research results emphasize the importance of transfer learning in making cybersecurity solutions adaptable and effective in the face of evolving malware threats.
Data Anonymization and Privacy Preservation in Healthcare Systems Krishnasheesh Datta, Himanshu Gupta EPJ Web of Conferences, 2025 The rapid development of digital technologies has enabled the creation of modern information systems; yet, it has also brought unprecedented challenges towards data security and user privacy. Sensitive data, especially in the healthcare, financial, and communication industries, are increasingly subject to violations and abuse. This study aims to strengthen data protection mechanisms through the integration of innovative data encryption and anonymization methods. It critically reviews various best-in-class approaches using both qualitative assessments and quantitative measures. With the objective to identify key trends and driving factors, a bibliometric analysis was performed using VOSviewer, which focuses on prominent authors, dominant research topics, and collaborative networks in data privacy. In addition, empirical case studies are examined to demonstrate the applicability and effectiveness of these methods in safeguarding user data. The study not only maps present progress but also outlines present vulnerabilities, offering insights for designing strong privacy-preserving systems. Finally, this study contributes to building a safer and more trustworthy digital world by strengthening the underlying constructs of data confidentiality, integrity, and user trust.
Implementing AI Driven Customer Support Chatbot Application 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Zero-Day Intrusion Detection via Byte-Level Packet Modeling Using PacketBER Poonam Kumari, Himanshu Gupta, Ashish Seth 2025 International Conference on Sustainable Technologies for Humanity and Smart World Hswtech 2025, 2025 As cyber threats get smarter and more difficult to detect, prompting zero-day attacks, the need for quick and sharp intrusion detection systems is increasing. Traditional IDS systems work best with known attacks, as they use simple signatures and protocol features. In this study, we propose PacketBERT which uses transformers to treat network packets as byte series and understand what they mean without the need for human-designed features. With progress in natural language processing, PacketBERT regards network data as language and studies the relationships between bytes in different packets. Tested with a synthetic attack dataset, the model results in 73.5% correct predictions, macro-average F1-score of 0.595 and ROC-AUC 0.545. Although modest by classical standards, these results show that transformers can help detect threats we have not seen yet. The technology paves the way for future detection systems that can identify attacks before they are seen by designers.
Enhancing Cloud Security: Analysis of Vulnerabilities and a Resilient Framework Proposal 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
A machine learning model for predicting phishing websites Grace Odette Boussi, Himanshu Gupta, Syed Akhter Hossain International Journal of Electrical and Computer Engineering, 2024 There are various types of cybercrime, and hackers often target specific ones for different reasons, such as financial gain, recognition, or even revenge. Cybercrimes are not restricted by geographical boundaries and can occur globally. The prevalence of specific types of cybercrime can vary from country to country, influenced by factors such as economic conditions, internet usage levels, and overall development. Phishing is a common cybercrime in the financial sector across different countries, with variations in techniques between developed and developing nations. However, the impact, often leading to financial losses, remains consistent. In our analysis, we utilized a dataset featuring 48 attributes from 5,000 phishing webpages and 5,000 legitimate webpages to predict the phishing status of websites. This approach achieved an impressive 98% accuracy.
Cyber Security Model for Threat Hunting Anchit Agarwal, Himdweep Walia, Himanshu Gupta 2021 9th International Conference on Reliability Infocom Technologies and Optimization Trends and Future Directions Icrito 2021, 2021
Data Storage Encryption with Passphrase Using Hybrid Algorithm Neeraj Kaushik, Mohammad Yawer Qadri, Himanshu Gupta 2021 9th International Conference on Reliability Infocom Technologies and Optimization Trends and Future Directions Icrito 2021, 2021
A Proposed Framework for Controlling Cyber- Crime Grace Odette Boussi, Himanshu Gupta Icrito 2020 IEEE 8th International Conference on Reliability Infocom Technologies and Optimization Trends and Future Directions, 2020
Impact of SQL Injection in Database Security Himanshu Gupta, Subhash Mondal, Srayan Ray, Biswajit Giri, Rana Majumdar, Ved P Mishra Proceedings of 2019 International Conference on Computational Intelligence and Knowledge Economy Iccike 2019, 2019
An Authentication Model for Secure Electronic Transaction Himanshu Gupta, Subhash Mondal, Biswajit Giri, Rana Majumdar, Neha Sana Ghosh, Ved P Mishra Proceedings of 2019 International Conference on Computational Intelligence and Knowledge Economy Iccike 2019, 2019
Impact of Side Channel Attack in Information Security Himanshu Gupta, Subhash Mondal, Rana Majumdar, Neha Sana Ghosh, Soumya Suvra Khan, Ngala Etienne Kwanyu, Ved P Mishra Proceedings of 2019 International Conference on Computational Intelligence and Knowledge Economy Iccike 2019, 2019
A Review of Security Issues in Mobile Banking Applications 11th Indiacom 4th International Conference on Computing for Sustainable Global Development Indiacom 2017, 2017
A hybrid model on cloud security Rahul Khurana, Himanshu Gupta 2016 5th International Conference on Reliability Infocom Technologies and Optimization Icrito 2016 Trends and Future Directions, 2016
Application based intrusion detection system International Journal of Control Theory and Applications, 2016
A security framework against ARP spoofing Ravi Raj Saini, Himanshu Gupta 2015 4th International Conference on Reliability Infocom Technologies and Optimization Trends and Future Directions Icrito 2015, 2015
