BlackBerry has patented a system using convolutional neural networks to classify scripts in disassembled binary files. The system processes instructions, detects sequences, and determines classifications based on the presence of these sequences. The output helps decide whether to execute, open, or access the corresponding binary file. GlobalData’s report on BlackBerry gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on BlackBerry, Adaptive video coding was a key innovation area identified from patents. BlackBerry's grant share as of February 2024 was 70%. Grant share is based on the ratio of number of grants to total number of patents.
System for training neural network to classify scripts in binary files
A recently granted patent (Publication Number: US11928213B2) discloses a system and method for analyzing disassembled binary files using a convolutional neural network. The system includes a processor and memory with program code to receive a disassembled binary file, generate fixed-length representations of instructions, and process the file with a trained convolutional neural network. The neural network applies different kernels to detect sequences of instructions and determines a classification for the file, providing an output to decide whether to execute, open, or access the corresponding binary file. The method involves encoding instructions, training the neural network with training files, and adjusting weight matrices to minimize errors in classification.
Furthermore, the system and method involve processing variable-length instructions by truncating or padding them to a fixed length while maintaining mnemonic associations. The convolutional neural network is trained using fixed-length representations of instructions and applies multiple kernels to detect specific sequences of instructions. The method includes steps for encoding instructions, training the network with training files, and adjusting weight matrices to improve classification accuracy. Overall, the patent aims to enhance the analysis of disassembled binary files by utilizing convolutional neural networks and fixed-length representations of instructions to determine the classification of files accurately.
To know more about GlobalData’s detailed insights on BlackBerry, buy the report here.
Premium 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.
