MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123136 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy Vishwavidyapeeth; Malla Reddy College Of Engineering And Technology; Malla Reddy Engineering College For Womens; Malla Reddy University; and Dr. Aravind B, Medchal-Malkajgiri, Telangana, on Dec. 6, 2025, for 'self-learning intrusion detection system for cloud workloads.'
Inventor(s) include Dr. Aravind B; Dr. Syed Mohd Faisal; I Uma Mahesh; Mrs. Peruri Sudheshna; Dr. G. Bala Krishna; and Dr. K. Pranathi.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "Various workloads in the cloud environment fluctuate with an incidence of frequency as the applications scale, migrate and serve user demand. Such dynamic environments make traditional methods of intrusion detection ineffective as the fixed rules and signature based models do not have the power to accommodate such changing patterns of attacks. One solution to this is a self learning intrusion detection system, in which the system continuously observes the workload behaviour and identifies deviations in the customary operation behaviour and alters the detection rules over time and with the changes in the cloud activity. The system collects telemetry of virtual machines, containers, serverless functions, as well as network flows and adds metrics of resource utilization, process activity, network flows, authentication transactions, and inter-service communications. The system builds a foundational representation of typical behaviour of every workload using learning models that are adaptive. In case of an emergence of a new activity, it is cross-matched with both short-term behaviour deviations and long-term tendencies in order to assess its potential description of malicious intent, misconfigurations, or components breaches. Depending on the severity, the system sends alerts or seals the impacted workload or implements the automated mitigation policies in case suspicious behaviour has been identified. The detection accuracy is improved in the future by using confirmed incidents, false positives and changes in the environment. This continuous learning process allows the system to change automatically as to how it responds to new threats and workload changes without having to re-write rules. The system enhances the cloud security, reduces the overhead of operation, as well as provides reliable security on the dynamically elastic, multi-tenant, environment of the cloud through behavioral analytics, anomaly detection and automatic adaptation."
Disclaimer: Curated by HT Syndication.
