Loading patent…
AssigneeNetskope, Inc.
InventorsSiying Yang, Xiaolin Wang, Krishna Narayanaswamy, Yi Zhang
Estimating the term…
The technology disclosed relates to distributing a trained master deep learning (DL) stack with stored parameters to a plurality of organizations, to detect organization sensitive data in images, referred to as image-borne organization sensitive documents, and protecting against loss of the image-borne organization sensitive documents. Disclosed is providing organizations with a DL stack update trainer, under the organizations' control, configured to allow the organizations to perform update training to generate updated DL stacks, without the organizations forwarding images of organization-sensitive training examples, and to save non-invertible features derived from the images, ground truth labels for the images, and parameters of the updated DL stacks. In particular, the technology disclosed relates to receiving, from a plurality of the DL stack update trainers, organization-specific examples including the non-invertible features of the organization-sensitive training examples and the ground truth labels, and using the received organization-specific examples to update the trained master DL stack.
A computer-implemented method of customizing a deep learning (abbreviated DL) stack to detect organization sensitive data in images, referred to as image-borne organization sensitive documents, and protecting against loss of the image-borne organization sensitive documents, including:
A tangible non-transitory computer readable storage media, including program instructions loaded into memory that, when executed on processors, cause the processors to implement a computer-implemented method of customizing a deep learning (abbreviated DL) stack to detect organization sensitive data in images, referred to as image-borne organization sensitive documents, and protecting against loss of the image-borne organization sensitive documents, the computer-implemented method including:
A computer-implemented method of customizing a deep learning (abbreviated DL) stack to detect organization sensitive data in images, referred to as image-borne organization sensitive documents, and protecting against loss of the image-borne organization sensitive documents, including:
A tangible non-transitory computer readable storage media, including program instructions loaded into memory that, when executed on processors, cause the processors to implement a computer-implemented method of customizing a deep learning (abbreviated DL) stack to detect organization sensitive data in images, referred to as image-borne organization sensitive documents, and protecting against loss of the image-borne organization sensitive documents, the computer-implemented method including:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
To a system of files or objects, e.g. local or distributed file system or database: protecting personal data, e.g. for financial or medical purposes
Protecting data: tools and structures for managing or administering access control systems
Architecture, e.g. interconnection topology: combinations of networks
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]
About 13 years 7 months of term left · ends 3 Jun 2040 (estimated)
The following materials are incorporated by reference in this filing:
U.S. Non-Provisional patent application Ser. No. 16/807,128, entitled “LOAD BALANCING IN A DYNAMIC SCALABLE SERVICES MESH,” filed on Mar. 2, 2020.
U.S. Non-Provisional application Ser. No. 14/198,508, entitled “SECURITY FOR NETWORK DELIVERED SERVICES”, filed on Mar. 5, 2014 (now U.S. Pat. No. 9,270,765, issued on Feb. 23, 2016),
In the drawings, like reference characters generally refer to like parts throughout the different views. Also, the drawings are not necessarily to scale, with an emphasis instead generally being placed upon illustrating the principles of the technology disclosed. In the following description, various implementations of the technology disclosed are described with reference to the following drawings.
FIG. 1A illustrates an architectural level schematic of a system for detecting identification documents in images, referred to as image-borne identification documents, and protecting against loss of the image-borne identification documents, while applying security services in the cloud. The disclosed system can also detect screenshot images and protect against loss of sensitive screenshot-borne data.
FIG. 1B illustrates image-borne sensitive data detection aspects of the architecture for detecting identification documents in images, referred to as image-borne identification documents, and protecting against loss of the image-borne identification documents, while applying security services in the cloud; and for detecting screenshot images and protecting against loss of sensitive screenshot-borne data.
The following detailed description is made with reference to the figures. Sample implementations are described to illustrate the technology disclosed, not to limit its scope, which is defined by the claims. Those of ordinary skill in the art will recognize a variety of equivalent variations on the description that follows.
The use of deep learning technologies enhances the detection of sensitive information in documents and images, detecting images with sensitive information without going through existing expensive OCR processes. Deep learning uses optimization to find the optimal parameter values for a model to make the best predictions. Deep learning based image classification typically requires a large number of labeled images with sensitive information, which are challenging to acquire at scale and this limitation hinders the adoption of deep learning based image classification in DLP products.
The disclosed innovations apply deep learning based image classification in data loss prevention (DLP) products, without the upfront need for a large number of labeled images with sensitive information. Many pre-trained generic deep learning models available today use public ImageNet datasets and other similar sources. These deep learning models are typically multi-layered convolutional neural networks (CNN) which have the capability of classifying general objects such as cats, dogs, cars, etc. The disclosed technology uses a small number of specialized labeled images, such as passports and drivers' license images, to re-train the last few layers of the CNN models. This way, the deep learning (DL) stack can detect these specific images with high accuracy, without requiring a large number of labeled images that contain sensitive data.