Netskope, Inc.

Truetel Communications, Inc.

Abhay Kulkarni

Krishna Narayanaswamy

Ravi Ithal

Lebin Cheng

Chetan Anand

Rajneesh Chopra

Steve Malmskog

Ariel Faigon

Jeevan Tambuluri

Willie Hsu

Ramana Devarapalli

The technology relates to machine responses to anomalies detected using machine learning based anomaly detection. In particular, to receiving evaluations of production events, prepared using activity models constructed on per-tenant and per-user basis using an online streaming machine learner that transforms an unsupervised learning problem into a supervised learning problem by fixing a target label and learning a regressor without a constant or intercept. Further, to responding to detected anomalies in near real-time streams of security-related events of tenants, the anomalies detected by transforming the events in categorized features and requiring a loss function analyzer to correlate, essentially through an origin, the categorized features with a target feature artificially labeled as a constant. An anomaly score received for a production event is determined based on calculated likelihood coefficients of categorized feature-value pairs and a prevalencist probability value of the production event comprising the coded features-value pairs.

Machine learning based anomaly detection initialization

The technology disclosed relates to a proxy receiving a request to manipulate a data object on an independent object store. The proxy is interposed between a user system from which the request originates and the independent object store. The technology disclosed further relates to the proxy accessing a metadata store that contains object metadata for the data object and retrieving the object metadata. The technology disclosed further relates to the proxy enforcing a policy on the request based on the object metadata. Enforcing the policy further includes enforcing malware detection policies and threat detection policies.

Cloud security based on object metadata

Machine learning based anomaly detection and response

The technology disclosed relates to machine learning based anomaly detection. In particular, it relates to constructing activity models on per-tenant and per-user basis using an online streaming machine learner that transforms an unsupervised learning problem into a supervised learning problem by fixing a target label and learning a regressor without a constant or intercept. Further, it relates to detecting anomalies in near real-time streams of security-related events of one or more tenants by transforming the events in categorized features and requiring a loss function analyzer to correlate, essentially through an origin, the categorized features with a target feature artificially labeled as a constant. It further includes determining an anomaly score for a production event based on calculated likelihood coefficients of categorized feature-value pairs and a prevalencist probability value of the production event comprising the coded features-value pairs.

Anomaly detection with machine learning

The technology disclosed relates to enforcing multi-part policies on data-deficient transactions of independent data stores. In particular, it relates to combining active analysis of access requests for the independent object stores with inspection of objects in the independent object stores, each of the analysis and inspection generating and persisting object metadata in a supplemental data store, actively processing data-deficient transactions that apply to the objects by accessing the supplemental data store to retrieve object metadata not available in transaction streams of the data-deficient transactions, and actively enforcing the multi-part policies using the retrieved object metadata.

Middle ware security layer for cloud computing services

Data loss prevention (DLP) policy enforcement based on object metadata

Systems and methods of enforcing multi-part policies on data-deficient transactions of cloud computing services

Metadata-based cloud security

Metadata-based data loss prevention (DLP) for cloud storage

Machine learning based anomaly detection

The present invention relates to the field of software-based services in communication networks. More particularly, it includes systems and methods for maintaining and utilizing routing data to handle event notifications generated by call handling in a service logic execution environment. Particular aspects of the present invention are described in the claims, specification and drawings.

SLEE service convergence and routing

Growing community of inventors

Cupertino, CA, United States of America

Abhay Kulkarni