Sharvari Chandrashekhar Tamane
Biography
An accomplished academician and administrator with 28+ years of experience in teaching, research, and academic leadership. Known for fostering a culture of academic excellence, Dr. Tamane has significantly contributed to the fields of Cloud Computing, Big Data, Cybersecurity, and more through innovative research, curriculum design, and mentorship. She is a passionate educator and strategic leader, actively engaged in institutional development and international collaborations.
Research Interest
• Leadership, Research Mentorship, Teaching, Curriculum Development, Program Management
• Cloud Computing, Big Data, Security, Blockchain, Neural Networks, Algorithms, Operating Systems
• Cloud Security, Blockchain, Fuzzy Logic, Wavelet Analysis, Watermarking, AI-based Security Systems
Abstract
Leveraging Artificial Intelligence for Proactive Cybersecurity: A Hybrid Framework for Threat Detection and Response
In today’s hyperconnected digital landscape, the rapid advancement of technologies brings both opportunities and threats. Cyberattacks have become more sophisticated, dynamic, and harder to detect using traditional security mechanisms. This paper proposes a hybrid framework that integrates artificial intelligence (AI), machine learning (ML), and behavioral analytics for real-time threat detection and autonomous response in cybersecurity environments. The framework is designed to analyze network traffic patterns, user behavior, and system anomalies using supervised and unsupervised ML techniques. It incorporates deep learning models such as recurrent neural networks (RNNs) for anomaly detection and reinforcement learning for adaptive response strategies. Special emphasis is placed on reducing false positives, enhancing detection accuracy, and ensuring minimal system disruption during automated interventions. The paper also explores the integration of explainable AI (XAI) to foster transparency and trust among cybersecurity professionals. Case studies and simulation results validate the efficacy of the proposed model in detecting zero-day attacks, phishing campaigns, and insider threats across enterprise networks. This research aligns with the broader goal of developing intelligent, resilient, and adaptive cybersecurity systems capable of defending against emerging threats in real time. The framework holds potential for deployment in critical infrastructure, defense, and cloud environments.
