The Future of Zero Trust and SASE is Now! Register now

close
close
The platform of the future is Netskope

Intelligent Security Service Edge (SSE), Cloud Access Security Broker (CASB), Cloud Firewall, Next Generation Secure Web Gateway (SWG), and Private Access for ZTNA built natively into a single solution to help every business on its journey to Secure Access Service Edge (SASE) architecture.

Go to Products Overview
Netskope video
Next Gen SASE Branch is hybrid — connected, secured, and automated

Netskope Next Gen SASE Branch converges Context-Aware SASE Fabric, Zero-Trust Hybrid Security, and SkopeAI-powered Cloud Orchestrator into a unified cloud offering, ushering in a fully modernized branch experience for the borderless enterprise.

Learn about Next Gen SASE Branch
People at the open space office
Designing a SASE Architecture For Dummies

Get your complimentary copy of the only guide to SASE design you’ll ever need.

Get the eBook
Embrace a Secure Access Service Edge (SASE) architecture

Netskope NewEdge is the world’s largest, highest-performing security private cloud and provides customers with unparalleled service coverage, performance and resilience.

Learn about NewEdge
NewEdge
Your Network of Tomorrow

Plan your path toward a faster, more secure, and more resilient network designed for the applications and users that you support.

Get the white paper
Your Network of Tomorrow
Netskope Cloud Exchange

The Netskope Cloud Exchange (CE) provides customers with powerful integration tools to leverage investments across their security posture.

Learn about Cloud Exchange
Netskope video
Make the move to market-leading cloud security services with minimal latency and high reliability.

Learn about NewEdge
Lighted highway through mountainside switchbacks
Safely enable the use of generative AI applications with application access control, real-time user coaching, and best-in-class data protection.

Learn how we secure generative AI use
Safely Enable ChatGPT and Generative AI
Zero trust solutions for SSE and SASE deployments

Learn about Zero Trust
Boat driving through open sea
Netskope achieves FedRAMP High Authorization

Choose Netskope GovCloud to accelerate your agency’s transformation.

Learn about Netskope GovCloud
Netskope GovCloud
  • Resources chevron

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

  • Blog chevron

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

  • Events & Workshops chevron

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

  • Security Defined chevron

    Everything you need to know in our cybersecurity encyclopedia.

Security Visionaries Podcast

Cookies, Not Biscuits
Host Emily Wearmouthas sits down with experts David Fairman and Zohar Hod to discuss the past, present, and future of internet cookies.

Play the podcast
Podcast: Cookies, Not Biscuits
Latest Blogs

How Netskope can enable the Zero Trust and SASE journey through security service edge (SSE) capabilities.

Read the blog
Sunrise and cloudy sky
SASE Week 2023: Your SASE journey starts now!

Replay sessions from the fourth annual SASE Week.

Explore sessions
SASE Week 2023
What is Security Service Edge?

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

Learn about Security Service Edge
Four-way roundabout
We help our customers to be Ready for Anything

See our Customers
Woman smiling with glasses looking out window
Netskope’s talented and experienced Professional Services team provides a prescriptive approach to your successful implementation.

Learn about Professional Services
Netskope Professional Services
The Netskope Community can help you and your team get more value out of products and practices.

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

Learn about Training and Certifications
Group of young professionals working
  • Company chevron

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

  • Why Netskope chevron

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

  • Leadership chevron

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

  • Partners chevron

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

Supporting sustainability through data security

Netskope is proud to participate in Vision 2045: an initiative aimed to raise awareness on private industry’s role in sustainability.

Find out more
Supporting Sustainability Through Data Security
Highest in Execution. Furthest in Vision.

Netskope recognized as a Leader in the 2023 Gartner® Magic Quadrant™ for Security Service Edge.

Get the report
Netskope recognized as a Leader in the 2023 Gartner® Magic Quadrant™ for Security Service Edge.
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 about Netskope Partners
Group of diverse young professionals smiling

AI and Deep Learning At Work: How to Know If Your Images Are Storing Sensitive Information

Jun 02 2023

In today’s rapidly digitizing world, the importance of data security has become paramount. With the increasing amount of sensitive information being shared and stored online, securing information from cyber attacks, information breaches, and theft has become a top priority for companies of all sizes. Data loss prevention (DLP) is a critical part of the Netskope Intelligent Security Service Edge (SSE) security platform, providing best-in-class data security to our customers. 

Images often contain a wealth of valuable and sensitive data. Financial documents, personal identification, and confidential business communications frequently include images that require the utmost security. At Netskope, we have developed state-of-the-art deep learning-based computer vision classifiers that can analyze images and identify sensitive information in a wide variety of categories such as passports, drivers licenses, credit cards, and screenshots. We have been awarded four U.S. patents for our innovative approach to data security. In this blog post, we highlight recent improvements to our image classifiers that resulted in higher accuracy and better customer experience.  

CNN Architecture Update

At the heart of our image classification models lie convolutional neural networks (CNNs). These powerful deep learning algorithms are specifically designed for image recognition and classification tasks. By employing a technique known as transfer learning, we take advantage of pre-existing CNNs that have been trained on large-scale datasets and fine-tune them using a smaller dataset of labeled images that contain sensitive information. As a result, our classifiers are able to quickly identify the unique patterns associated with the sensitive information, with high accuracy and reduced training time. 

There are several practical concerns in selecting the pre-trained CNN models. Given that our classifiers are used to scan millions of customer files daily by our SSE platform, it is crucial to keep false positives as low as possible to avoid overwhelming customers with spurious alerts. Simultaneously, since true positives indicate a serious data leak, maintaining a high true positive rate is equally important. An additional challenge lies in creating classifiers complex enough to meet our accuracy goals yet compact enough to fulfill our stringent latency requirements, since they run in real time on the SSE platform. As such, we only considered pre-trained CNN model architectures with fewer than 10 Million parameters.

EfficientNet Architecture (https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html)

In our latest model update, we transitioned to EfficientNet pre-trained CNN architecture (modeled in the figure above). This lead to an 80% increase in the number of model parameters. Using a larger pre-trained model incurred a modest increase in latency but yielded a significant boost in real-world accuracy. 

Training on real cloud data

In order to minimize false positives, it is important for our image classifiers to be exposed to a wide variety of realistic negative samples. To achieve this, we have sourced tens of thousands of actual cloud images from our own corporate data. This approach enables us to collect a substantial number of genuine training images, while simultaneously maintaining our commitment to customer privacy. These images were labeled by hand, with the majority of them being either negative examples or screenshots typical of real-world cloud data. 

In addition to these random negative examples, we have also incorporated several thousand carefully curated adversarial samples, further bolstering our classifiers’ resilience against false positives. One interesting type of adversarial sample was labels for electronics. Due to their bold fonts and high contrast coloring, they can be mistaken for sensitive documents. By training our classifiers on these adversarial examples, we can effectively prevent such misclassifications in the production environment.

Custom data augmentations

Example of image augmentation. A training sample of a driver’s license is pasted on a realistic background, in this case a screenshot.

In addition to sourcing real cloud data, we employ a comprehensive suite of data augmentation techniques specifically designed for computer vision applications, such as rotation and cropping. What sets our approach apart is the customization of these augmentations to ensure maximum fidelity with the image data encountered in real cloud environments. One example is our custom augmentation that seamlessly integrates documents onto realistic backgrounds, such as a driver’s license pasted on a screenshot. This enables our classifiers to train on documents in a diverse range of settings, significantly boosting its versatility and performance on real-world data.

Summary

In our pursuit to develop cutting-edge AI security solutions, we continuously strive to refine our methodologies and data sources to build powerful, adaptive data security models capable of safeguarding the ever-evolving digital landscape.

To learn more about how Netskope helps customers protect their sensitive data everywhere across their entire enterprise, please visit Netskope Data Loss Prevention.  And to keep up with with what our AI Labs team is writing about, please visit our AI Labs blog page here.

author image
Jason Bryslawskyj
At Netskope, Jason has been developing computer vision models for data loss prevention and phishing detection.

Stay informed!

Subscribe for the latest from the Netskope Blog