MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641113396 A) filed by Mr. G. Praveen Kumar; Dr. J. Justina Michael; Dr. Madhan Veeramani; Nalini. S; Dr. A. Selvapandian; Azm Hussain; Dr. Biswajit Datta; and Dr. Beaulah Princiba D on September 22, 2026, for Phishing Detection And Prevention Using Quantum Machine Learning And Quantum Cryptography.
Inventors include Mr. G. Praveen Kumar; Dr. J. Justina Michael; Dr. Madhan Veeramani; Nalini. S; Dr. A. Selvapandian; Azm Hussain; Dr. Biswajit Datta; and Dr. Beaulah Princiba D.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: Phishing constitutes a sort of cybercrime wherein perpetrators deceive unwary internet users into disclosing confidential information, leading to identity theft and monetary loss. As this menace escalates, artificial intelligence methodologies have surfaced as a viable remedy for its identification in recent years. Nonetheless, traditional machine learning methodologies are beginning to exhibit constraints, as training on extensive datasets under typical computer settings may either need excessive time for precise outcomes or yield subpar accuracy with expedited training. Phishing continues to pose a significant cybersecurity risk, however the utilisation of quantum machine learning (QML) for phishing detection is still in its nascent phase. This research offers a comprehensive literature analysis designed to deliver a succinct summary of current QML-based methodologies for phishing detection, highlighting methodological patterns, constraints, and prospective avenues for future inquiry. Eligible research was examined concerning QML models, feature encoding techniques, experimental configurations, assessment metrics, and study quality utilising a modified Newcastle–Ottawa Scale. The findings suggest that existing studies are sparse and predominantly concentrate on hybrid quantum-classical frameworks, especially quantum support vector machines and variational quantum classifiers. Prevalent obstacles encompass limited datasets, insufficient external validation, hardware interference, scalability limitations, and the lack of uniform benchmarks. Quantum computing and machine learning offer a whole novel framework for sophisticated approaches in cybersecurity. The immense processing capabilities of quantum computing will swiftly address complex cryptography challenges that traditional computers struggle with, hence offering enhanced encryption and decryption methods. Simultaneously, machine learning algorithms recognise evolving cyber dangers; they discern intricate patterns within extensive datasets and offer immediate forecasts of potential weaknesses.
Disclaimer: Curated by HT Syndication.
