Skip to content
Log in

Author

P. Paul

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

ELEVATING PHISHING DETECTION PERFORMANCE WITH MACHINE LEARNING AND DEEP LEARNING-ENABLED FEATURE SELECTION

Phishing remains one of the most persistent and rapidly evolving cybersecurity threats, exploiting deceptive websites, malicious URLs, fraudulent messages, compromised domains, and social-engineering strategies to obtain sensitive information such as usernames, passwords, financial credentials, personal records, and authentication tokens. Conventional phishing detection mechanisms based on blacklists, manually defined rules, static signatures, and heuristic filters provide useful protection against previously identified attacks but often exhibit limited effectiveness against zero-day phishing websites, short-lived malicious domains, obfuscated URLs, and dynamically changing attack patterns. Furthermore, machine learning-based phishing detection models frequently process large and redundant feature spaces containing irrelevant, correlated, or noisy attributes, which may increase computational overhead and reduce generalization capability. This research proposes an intelligent phishing detection framework that integrates machine learning, deep learning-enabled feature selection, multi-source phishing feature extraction, hybrid classification, and real-time risk assessment. The proposed framework extracts URL lexical characteristics, domain and host-based properties, webpage content indicators, Hypertext Markup Language and JavaScript features, security certificate attributes, redirection behavior, and contextual metadata. A deep learningenabled feature selection module employs representation learning and importance estimation to identify the most discriminative phishing indicators while eliminating redundant and low-contribution attributes. The selected feature subset is subsequently evaluated using machine learning classifiers such as Random Forest, Support Vector Machine, XGBoost, and Logistic Regression, together with deep learning architectures including Multilayer Perceptron, Convolutional Neural Network, and Long Short-Term Memory networks. A hybrid decision engine combines model confidence, anomaly indicators, and contextual risk information to classify web resources as legitimate, suspicious, or phishing. The proposed architecture consists of five interconnected layers: Data Acquisition, Preprocessing and Feature Engineering, Deep Learning-Enabled Feature Selection and Intelligent Detection, Risk Assessment and Response, and Application/User layers. Illustrative conceptual evaluation demonstrates that the proposed hybrid framework can achieve higher detection accuracy, precision, recall, F1-score, and lower response latency than blacklist-based, conventional machine learning, and standalone deep learning approaches. The framework provides a scalable foundation for intelligent phishing protection across browsers, email gateways, enterprise networks, financial platforms, educational environments, and cloud-based security services.

P. Paul, Bharath Bhushan, Bandameedi Sai Charan et al. · 0 citations
Open access Jun 2026

CYBER THREAT FORECASTING: THE TRANSITION FROM TRADITIONAL ML TO GENERATIVE AI APPROACHES

The increasing sophistication of cyber threats has created significant challenges for organizations in protecting digital infrastructures, sensitive information, and critical services. Traditional cybersecurity solutions based on signature matching and rule-based systems are often unable to detect emerging attack patterns, zero-day vulnerabilities, and advanced persistent threats in dynamic network environments. Machine Learning (ML) has improved cyber threat detection by enabling intelligent classification of malicious activities using historical security data. However, conventional ML models often require extensive feature engineering and exhibit limited adaptability to evolving attack behaviors. Recent advances in Generative Artificial Intelligence (Generative AI) have transformed cybersecurity by enabling intelligent threat forecasting, automated attack simulation, synthetic data generation, adaptive anomaly detection, and proactive security analysis. This paper presents a comprehensive framework for cyber threat forecasting by integrating traditional machine learning techniques with advanced Generative AI models. The proposed framework utilizes network traffic analysis, system logs, user behavior analytics, threat intelligence feeds, and security event data to predict future cyber threats. Comparative analysis is performed using conventional machine learning algorithms and Generative AI approaches to evaluate forecasting accuracy, prediction capability, and computational efficiency. Experimental results demonstrate that Generative AI significantly improves cyber threat prediction accuracy, reduces false-positive rates, enhances adaptive learning, and supports real-time security decision-making. The proposed framework contributes to the development of intelligent cybersecurity systems capable of proactively forecasting cyber threats and strengthening organizational resilience against rapidly evolving cyberattacks.

P. Paul, Bharath Bhushan, Bathini Revanth et al. · 0 citations