close
close
Your Network of Tomorrow
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.
          Experience Netskope
          Get Hands-on With the Netskope Platform
          Here's your chance to experience the Netskope One single-cloud platform first-hand. Sign up for self-paced, hands-on labs, join us for monthly live product demos, take a free test drive of Netskope Private Access, or join us for a live, instructor-led workshops.
            A Leader in SSE. Now a Leader in Single-Vendor SASE.
            A Leader in SSE. Now a Leader in Single-Vendor SASE.
            Netskope debuts as a Leader in the Gartner® Magic Quadrant™ for Single-Vendor SASE
              Securing Generative AI for Dummies
              Securing Generative AI for Dummies
              Learn how your organization can balance the innovative potential of generative AI with robust data security practices.
                Modern data loss prevention (DLP) for Dummies eBook
                Modern Data Loss Prevention (DLP) for Dummies
                Get tips and tricks for transitioning to a cloud-delivered DLP.
                  Modern SD-WAN for SASE Dummies Book
                  Modern SD-WAN for SASE Dummies
                  Stop playing catch up with your networking architecture
                    Understanding where the risk lies
                    Advanced Analytics transforms the way security operations teams apply data-driven insights to implement better policies. With Advanced Analytics, you can identify trends, zero in on areas of concern and use the data to take action.
                        The 6 Most Compelling Use Cases for Complete Legacy VPN Replacement
                        The 6 Most Compelling Use Cases for Complete Legacy VPN Replacement
                        Netskope One Private Access is the only solution that allows you to retire your VPN for good.
                          Colgate-Palmolive Safeguards its "Intellectual Property” with Smart and Adaptable Data Protection
                          Colgate-Palmolive Safeguards its "Intellectual Property” with Smart and Adaptable Data Protection
                            Netskope GovCloud
                            Netskope achieves FedRAMP High Authorization
                            Choose Netskope GovCloud to accelerate your agency’s transformation.
                              Let's Do Great Things Together
                              Netskope’s partner-centric go-to-market strategy enables our partners to maximize their growth and profitability while transforming enterprise security.
                                Netskope solutions
                                Netskope Cloud Exchange
                                Netskope Cloud Exchange (CE) provides customers with powerful integration tools to leverage investments across their security posture.
                                  Netskope Technical Support
                                  Netskope Technical Support
                                  Our qualified support engineers are located worldwide and have diverse backgrounds in cloud security, networking, virtualization, content delivery, and software development, ensuring timely and quality technical assistance
                                    Netskope video
                                    Netskope Training
                                    Netskope training will help you become a cloud security expert. We are here to help you secure your digital transformation journey and make the most of your cloud, web, and private applications.

                                      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.
                                      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