Sophos had 23 patents in artificial intelligence during Q4 2023. Sophos Ltd filed patents in Q4 2023 related to machine learning for identifying potentially malicious commands, prioritizing security events, recognizing malware in portable executable files, classifying computer systems as critical or non-critical, and restricting processes on user devices based on security threats. These patents involve utilizing historical data, training machine learning models, and automating security threat remediation based on user responses. GlobalData’s report on Sophos gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Sophos grant share with artificial intelligence as a theme is 21% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Methods and apparatus for machine learning to generate a decision tree database to identify commands similar to a command of interest (Patent ID: US20230403286A1)
The patent filed by Sophos Ltd. describes a method and apparatus for identifying potentially malicious commands by analyzing a plurality of features and traversing a decision tree to determine the probability of the command being malicious. The method involves identifying nodes associated with specific features, determining probabilities based on sets of similar commands, and displaying relevant information to users. The apparatus includes hardware processors and memory to execute the instructions for identifying, determining probabilities, and displaying information related to potentially malicious behaviors based on features and sets of similar behaviors.
The method and apparatus further involve displaying text descriptions of similar commands, updating nodes in the decision tree, and automatically performing remedial actions based on predetermined ranges of probabilities or indications. The patent also covers the use of multiple models to analyze behaviors, determine probabilities, and display relevant information to users. Additionally, the non-transitory processor-readable medium stores instructions for receiving potentially malicious commands, traversing nodes in a decision tree, determining probabilities, and displaying indications to quantify similar commands and probabilities. The decision tree is trained to be traversed using a greedy algorithm, enhancing the efficiency of identifying potentially malicious behaviors.
To know more about GlobalData’s detailed insights on Sophos, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
