Netskope named a Leader in the 2022 Gartner® Magic Quadrant™ for Security Service Edge. Get the Report.

  • Platform

    Unrivaled visibility and real-time data and threat protection on the world's largest security private cloud.

  • Products

    Netskope products are built on the Netskope Security Cloud.

Netskope delivers a modern cloud security stack, with unified capabilities for data and threat protection, plus secure private access.

Explore our platform
Birds eye view metropolitan city

Netskope Named a Leader in the 2022 Gartner Magic Quadrant™ for SSE Report

Get the report Go to Products Overview
Netskope gartner mq 2022 sse leader

Make the move to market-leading cloud security services with minimal latency and high reliability.

Learn more
Lighted highway through mountainside switchbacks

Prevent threats that often evade other security solutions using a single-pass SSE framework.

Learn more
Lighting storm over metropolitan area

Zero trust solutions for SSE and SASE deployments

Learn more
Boat driving through open sea

Netskope enables a safe, cloud-smart, and fast journey to adopt cloud services, apps, and public cloud infrastructure.

Learn more
Wind turbines along cliffside
  • Customer Success

    Secure your digital transformation journey and make the most of your cloud, web, and private applications.

  • Customer Support

    Proactive support and engagement to optimize your Netskope environment and accelerate your success.

  • Training and Certification

    Netskope training will help you become a cloud security expert.

Trust Netskope to help you address evolving threats, new risks, technology shifts, organizational and network changes, and new regulatory requirements.

Learn more
Woman smiling with glasses looking out window

We have qualified engineers worldwide, with diverse backgrounds in cloud security, networking, virtualization, content delivery, and software development, ready to give you timely, high-quality technical assistance.

Learn more
Bearded man wearing headset working on computer

Secure your digital transformation journey and make the most of your cloud, web, and private applications with Netskope training.

Learn more
Group of young professionals working
  • Resources

    Learn more about how Netskope can help you secure your journey to the cloud.

  • Blog

    Learn how Netskope enables security and networking transformation through security service edge (SSE).

  • Events & Workshops

    Stay ahead of the latest security trends and connect with your peers.

  • Security Defined

    Everything you need to know in our cybersecurity encyclopedia.

Security Visionaries Podcast

Bonus Episode: The Importance of Security Service Edge (SSE)

Play the podcast
Black man sitting in conference meeting

Read the latest on how Netskope can enable the Zero Trust and SASE journey through security service edge (SSE) capabilities.

Read the blog
Sunrise and cloudy sky

Netskope CSO speaking events

Meet the Netskope CSO team at one of our upcoming events.

Find an event
Netskope CSO Team

What is Security Service Edge?

Explore the security side of SASE, the future of network and protection in the cloud.

Learn more
Four-way roundabout
  • Company

    We help you stay ahead of cloud, data, and network security challenges.

  • Why Netskope

    Cloud transformation and work from anywhere have changed how security needs to work.

  • Leadership

    Our leadership team is fiercely committed to doing everything it takes to make our customers successful.

  • Partners

    We partner with security leaders to help you secure your journey to the cloud.

Netskope enables the future of work.

Find out more
Curvy road through wooded area

Netskope is redefining cloud, data, and network security to help organizations apply Zero Trust principles to protect data.

Learn more
Switchback road atop a cliffside

Thinkers, builders, dreamers, innovators. Together, we deliver cutting-edge cloud security solutions to help our customers protect their data and people.

Meet our team
Group of hikers scaling a snowy mountain

Netskope’s partner-centric go-to-market strategy enables our partners to maximize their growth and profitability while transforming enterprise security.

Learn more
Group of diverse young professionals smiling
Blog Data Science In the Blink of AI — How Artificial Intelligence is Changing the Way Enterprises Protect Sensitive Data in Images
Jul 27 2020

In the Blink of AI — How Artificial Intelligence is Changing the Way Enterprises Protect Sensitive Data in Images

Co-authored by Yihua Liao and Yi Zhang

You have probably heard of how AI technology is used to recognize cats, dogs and humans in images, a task known as image classification. The same technology that identifies a cat or dog – can also identify sensitive data (such as identification cards and medical records) in images traversing your corporate network. In this blog post, we will show you how we use convolutional neural networks (CNN), transfer learning, and generative adversarial networks (GAN) to provide image data protection for Netskope’s enterprise customers. 

Image Data Security

Images represent over 25% of the corporate user traffic that goes through Netskope’s Data Loss Prevention (DLP) platform. Many of these images contain sensitive information, including customer or employee personally identifiable information (PII) (e.g., pictures of passports, driver’s licenses, and credit cards), screenshots of intellectual property, and confidential financial documents. By detecting sensitive information in images, documents, and application traffic flows, we help organizations comply with compliance regulations and protect their assets.

The traditional approach to identifying sensitive data in an image has been to use optical character recognition (OCR) to extract text out of the image. The extracted text is then used for pattern matching. This technology, though effective, is resource-intensive and delays detection of security violations. OCR also has difficulties identifying violations in low-quality images. In many cases, we only need to determine the classification of the input image. For example, we would like to find out whether an image is a credit card or not, without knowing the 16-digit card number and other details in the image. Machine learning-based image classification is an ideal choice for that because of its accuracy, speed and ability to work inline with granular policy controls. We can also combine image classification with OCR to generate more detailed violation alerts. 

CNN and Transfer Learning

Deep learning and convolutional neural networks (CNN) were a huge breakthrough in image classification in the early 2010s. Since then, CNN-based image classification has been applied to many different domains, including medicine, autonomous vehicles, and security, with accuracy close to that of humans. Inspired by how the human visual cortex works, a CNN is able to effectively capture the shapes, objects and other qualities to better understand the contents of the image. A typical CNN has two parts (depicted in the chart below):

  • The convolutional base, which consists of a stack of convolutional and pooling layers. The main goal of the convolutional base is to generate features from the image. It builds progressively higher-level features out of an input image. The early layers refer to general features, such as edges, lines, and dots in the image. Meanwhile, the latter layers refer to task-specific features, which are more human interpretable,  such as the logo on a credit card, or application windows in a screenshot. 
  • The classifier, which is usually composed of fully connected layers. Think of the classifier as a machine that sorts the features identified in the convolutional base. The classifier will tell you if the features identified are a cat, dog, drivers license, or X-ray.
Diagram of CNN and transfer learning
Image Source: DOI: 10.3390/electronics8030292

You may need millions of labeled images to train a CNN from scratch in order to achieve state-of-the-art classification accuracy. It is not trivial to collect a large number of images with proper labels, especially when you are dealing with sensitive data such as passports and credit cards. Fortunately, we can use transfer learning, a popular deep learning technique, to train a neural network with just hundreds or thousands of training samples. With transfer learning, we can leverage an existing convolutional neural network (e.g., ResNet or MobileNet) that was trained on a large dataset to classify other objects, and tweak it to train with additional images. Transfer learning allows us to train a CNN image classifier with a limited dataset and still achieve good performance while significantly reducing the training time.

Synthetic Training Data Generation

It’s very challenging to acquire real images for the sensitive categories we are interested in. To increase the amount and diversity of the training dataset and further improve the accuracy of CNN classifiers, we use generative adversarial networks (GAN) to generate synthetic training data. The basic idea of a GAN is to create two neural networks (high-level architecture diagram below), which compete against each other. One neural network, called the generator, generates fake data, while the other, the discriminator, evaluates them for authenticity. The goal is to generate data that is similar to the training data and fool the discriminator.

Diagram of GAN
Image Source: Deep Convolutional Generative Adversarial Networks

With a GAN, we are able to synthesize photorealistic images with varying degrees of change in rotation, color, blurring, background, and so on. Here are a few examples of the synthetic images:

Examples of synthetic images

Netskope’s Inline DLP Image Classifiers

At Netskope, we have developed CNN-based image classifiers, as part of our Next Gen SWG and cloud inline solutions covering managed apps, unmanaged apps, custom apps, and public cloud service user traffic. The classifiers are able to accurately identify images with sensitive information, including passports, driver’s licenses, US social security cards, credit cards and debit cards, fullscreen and application screenshots, etc. The inline classifiers provide granular policy controls in real-time.

Examples of passports, drivers licenses, social security numbers, and credit/debit cards
Screenshots of examples

Future Work

At Netskope, we are actively expanding our portfolio of inline image classifiers with the latest computer vision technology. We also have the capability to train custom classifiers and identify new types of images that our customers are interested in classifying. If your organization has unique assets that may be shared in images and you’d like to protect those assets, please contact us at [email protected] to learn more.

author image
About the author
Dr. Yihua Liao is the Director of Data Science at Netskope. His team Develops cutting-edge AI/ML technology to tackle many challenging problems in cloud security, including data loss prevention, malware and threat protection, and user/entity behavior analytics. Previously, he led data science teams at Uber and Facebook.
Dr. Yihua Liao is the Director of Data Science at Netskope. His team Develops cutting-edge AI/ML technology to tackle many challenging problems in cloud security, including data loss prevention, malware and threat protection, and user/entity behavior analytics. Previously, he led data science teams at Uber and Facebook.