Palo Alto Networks had 18 patents in artificial intelligence during Q1 2024. Palo Alto Networks Inc filed patents in Q1 2024 for various techniques related to cybersecurity. These include an OCR filter for sensitive customer data, innocent until proven guilty (IUPG) solutions for deep learning models, detecting parked domains using machine learning, classifying API response fields for security policies, and self-learning malware detection based on sample traffic analysis. These innovations aim to enhance security measures and improve threat detection capabilities. GlobalData’s report on Palo Alto Networks gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Palo Alto Networks grant share with artificial intelligence as a theme is 33% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Optical character recognition filtering (Patent ID: US20240062569A1)

The patent filed by Palo Alto Networks Inc. describes a method and system for filtering non-textual files in scanned customer data using an OCR filter trained on labeled files with optical character recognition (OCR) features. The OCR filter classifies files as textual or non-textual based on training data and internal representations to avoid leaking sensitive customer data. The performance of the OCR filter is evaluated based on false positive and false negative rates, ensuring continued model performance and informing updates. The method involves scanning a data stream, classifying files with a machine learning model, filtering non-textual image data files, and communicating the filtered files for OCR and security analysis.

The system further includes features such as determining potentially sensitive text in image data, evaluating the machine learning model's classifications with sampled files, updating the model based on performance thresholds, and utilizing a convolutional neural network for classification. The patent also covers the generation of feature values for training files, determining labels based on these values, and training a machine learning model to filter non-textual image data. Additionally, the apparatus described includes a processor and computer-readable medium with instructions for determining labels, inputting files into different components of a machine learning model, storing representations for training, and training the model on stored representations and labels. The system architecture involves a CNN with specific internal layers for processing the training data and making classifications based on optical recognition features.

To know more about GlobalData’s detailed insights on Palo Alto Networks, 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

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.