Zscaler, Inc.

Changsha Ma

Howie Xu

Rex Shang

Dianhuan Lin

Narinder Paul

Shashank Gupta

Parnit Sainion

Douglas A Koch

Deepen Desai

Tarun Dewan

Visvanathan Thothathri

Kevin Guo

Bharath Kumar

Bharath Meesala

Uday Pratap Singh

Naveen Selvan

Nirmal Singh

Rakshitha Hedge

Dong Guo

Systems and methods of sandboxing a file include responsive to receiving a file associated with a user, obtaining policy for the user; analyzing the file with a machine learning model; and based on a combination of the policy for the user and a verdict of the machine learning model, one of quarantining the file for analysis in a sandbox and allowing the file to the user. The present disclosure presents a smart quarantine with a goal of minimizing the number of files quarantined, the number of malicious files passed through to an end user, and a number of files scanned by a sandbox.

Utilizing machine learning for smart quarantining of potentially malicious files

Systems and methods include receiving content for classification; classifying the content as one of benign and malicious utilizing a model that has been trained with a training set of data including benign data and malicious data; determining a first pattern associated with the content; comparing the first pattern with a second pattern that is associated with one of the benign data and the malicious data; and determining an uncertainty of the classifying based on a distance between the first pattern and the second pattern. The systems and methods can include discarding the classification if the distance is greater than a configurable threshold.

Pattern similarity measures to quantify uncertainty in malware classification

Systems and methods include performing inline monitoring of production traffic between users, the Internet, and cloud services via a cloud-based system; utilizing a trained machine learning model to inspect static properties of files in the production traffic; and classifying the traffic as one of malicious or benign based on the trained machine learning model.

Utilizing machine learning to detect malicious executable files efficiently and effectively

Systems and methods include receiving a trained machine learning model that has been processed with training information removed therefrom, wherein the training information is utilized in training of the trained machine learning model; monitoring traffic, inline at the node, including processing the traffic with the trained machine learning model; obtaining a verdict on the traffic based on the trained machine learning model; and performing an action on the traffic based on the verdict.

Machine learning model abstraction layer for runtime efficiency

Systems and methods include determining a plurality of features associated with executable files, wherein the plurality of features are each based on static properties in predefined structure of the executable files; obtaining training data that includes samples of benign executable files and malicious executable files; extracting the plurality of features from the training data; and utilizing the extracted plurality of features to train a machine learning model to detect malicious executable files.

Utilizing Machine Learning to detect malicious executable files efficiently and effectively

Systems and methods include obtaining file identifiers associated with files in production data; obtaining lab data from one or more public repositories of malware samples based on the file identifiers for the production data; and utilizing the lab data for training a machine learning process for classifying malware in the production data. The obtaining file identifiers can be based on monitoring of users associated with the files, and only the file identifiers are maintained based on the monitoring. The lab data can include samples from the one or more public repositories matching the corresponding file identifiers for the production data. The lab data can include samples from the one or more public repositories that have features closely related to features of the production data.

Building a Machine Learning model without compromising data privacy

Systems and methods include obtaining a file associated with a user for processing; utilizing a combination of policy for the user and machine learning to determine whether to i) quarantine the file and scan the file in a sandbox, ii) allow the file to the user and scan the file in the sandbox, and iii) allow the file to the user without the scan; responsive to the quarantine of the file and the sandbox determining the file is malicious, blocking the file; and, responsive to the quarantine of the file and the sandbox determining the file is benign, allowing the file.

Systems and methods include receiving a content item between a user device and a location on the Internet or an enterprise network; utilizing a trained machine learning ensemble model to determine whether the content item is malicious; responsive to the trained machine learning ensemble model determining the content item is malicious or determining the content item is benign but such determining is in a blind spot of the trained ensemble model, performing further processing on the content item; and, responsive to the trained machine learning ensemble model determining the content item is benign with such determination not in a blind spot of the trained machine learning ensemble model, allowing the content item. A blind spot is a location where the trained machine learning ensemble model has not seen any examples with a combination of features at the location or has examples with conflicting labels.

Prudent ensemble models in machine learning with high precision for use in network security

Systems and methods include training a machine learning model with data for identifying features in monitored traffic in a network; analyzing the trained machine learning model to identify information overhead therein, wherein the information overhead is utilized in part for the training; removing the information overhead in the machine learning model; and providing the machine learning model for runtime use for identifying the features in the monitored traffic, with the removed information overhead from the machine learning model.

Growing community of inventors

Campbell, CA, United States of America

Changsha Ma