METHOD AND SYSTEM FOR DETECTING MALICIOUS APPLICATIONS

• Main Authors: PUTTAGUNTA, Vasundhara, BIJU, Emil, NAGARALU, Sree Hari, SR, Venkatachalabathy, MOTHILAL, Sudarson, SEWAK, Mohit, JODHA, Rituraj, MANYAM, Supreeth
• Format: Patent
• Language: English; French; German
• Published: 19.06.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

A method comprising: selecting among a plurality of features corresponding with application-related entities, a set of candidate features defining a feature space for determining application maliciousness; receiving data of a first application and a second application; determining the first application and second application are linked by a common application-related entity; identifying a feature-based relationship between the first application and the second application based on a distance metric applied to the first feature vector and the second feature vector in the feature space of the first feature vector and the second feature vector; generating a neighbor association between the first application and the second application based on the feature-based relationship identified between the first application and the second application; validating the set of candidate features based on the neighbor association, the first known threat status of the first application and the second known threat status of the second application.