MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641090673 A) filed by St. Peter'S Engineering College on July 25, 2026, for Dynamic Threat Detection And Mitigation System Using Machine Learning And Block Chain Technology.
Inventors include Ms. Gudimetta Sreelalitha, Assistant Professor In Department Of; Mr. Katha Chandrashekhar, Assistant Professor In Department Of Cse, St Peters Engineering College, Opposite Ts Forest Academy, Kompally; Mr. Shivakumar M, Assistant Professor In Department Of Cseaiml, St; Mr. Rekhansh Rao, Assistant Professor In Department Of Cseaiml, St; Ms. Trupti Deshkar, Assistant Professor In Department Of Cseaiml, St; and Mr. Mulkala Pradeep, Assistant Professor In Department Of Cseaiml, St Peters Engineering College, Opposite Ts Forest Academy, Kompally Road, Dullapally, Maisammaguda, Medchal, Hyderabad, Telangana.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: The present invention relates to a Dynamic Threat Detection and Mitigation System Using Machine Learning and Block chain Technology for intelligent cyber security in distributed computing environments. The proposed system integrates advanced machine learning algorithms with block chain technology to enable real-time threat detection, secure event management, and automated cyber attack mitigation. The system comprises a Data Acquisition Module, Data Preprocessing Module, Machine Learning-Based Threat Detection Engine, Block chain Security Layer, Threat Mitigation Module, and Continuous Learning Module. Security data collected from network traffic, endpoint devices, cloud platforms, Internet of Things (IoT) devices, and system logs are preprocessed and analyzed using supervised, unsupervised, and deep learning models to identify malware, phishing attacks, ransomware, distributed denial-of-service (DDoS) attacks, insider threats, unauthorized access, and zero- day attacks. The block chain security layer stores threat records and mitigation actions in an immutable distributed ledger using cryptographic hashing and smart contracts, ensuring secure, transparent, and tamper-resistant management of cyber security events. Upon threat detection, the mitigation module automatically executes predefined response actions, including malicious IP blocking, device isolation, firewall rule updates, and administrator alerts to minimize security risks. The continuous learning framework periodically retrains machine learning models using newly acquired threat intelligence, enabling adaptive protection against emerging cyber threats. The proposed invention provides a scalable, decentralized, secure, and self-learning cyber security platform that significantly improves threat detection accuracy, response efficiency, data integrity, and overall cyber resilience for enterprise networks, cloud infrastructures, healthcare systems, financial institutions, industrial control systems, and smart city applications.
Disclaimer: Curated by HT Syndication.
