Skip to main content
  • EN

Artificial Intelligence and Machine Learning

This forum is created by Netskope AI Labs to keep you informed about the latest updates and developments regarding AI-powered features in the Netskope platform. Our goal is to provide a space where you can ask questions, share your experiences, and connect with the community to learn about AI. we invite you to be a part of the AI conversation and explore the possibilities of AI!

  • 23 Topics
  • 17 Replies
23 Topics
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
New AI/ML Patents on IoT Device Intelligence and Policy Engines

Netskope has been granted three new U.S. patents for its innovative approaches to IoT security and AI/ML based policy engines. Middle-ware artificial intelligence (AI) engine (US 12,166,776, Dec. 2024) Systems and methods for computing device association (US 12,137,389, Nov. 2024) Machine learning based policy engine preference for data access (US 12,126,655, Oct. 2024)These patents enhance Netskope's comprehensive intellectual property portfolio and solidify its competitive position in the industry. 

400
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
New Blog Post: Proactive App Connector Monitoring with Machine Learning

App connectors are a critical component of the Netskope secure access service edge (SASE) platform, offering visibility into user activities based on their interactions with cloud applications. These connectors monitor various types of user actions, such as uploads, downloads, and sharing events in apps like Google Drive and Box, by analyzing network traffic patterns. With this visibility, security administrators can then configure and enforce real-time policies to prevent malware, data theft and exfiltration.we’ve developed a patent-pending app activity monitoring system that leverages advanced machine learning algorithms to automatically identify significant anomalies in app event counts. Please read our latest blogpost for details: https://www.netskope.com/blog/proactive-app-connector-monitoring-with-machine-learning 

560
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Netskope's New Patents on URL Categorization and DLP File Classification

Netskope has been granted two new U.S. patents for its pioneering work in URL categorization and sensitive file classification, recognizing the company's innovative approaches to these critical areas. Specifically, the patents acknowledge Netskope's expertise in the following technologies:Machine learning-based URL categorization system with selection between more and less specific category labels (Patent number: 12,081,550) Training and configuration of DL stack to detect attempted exfiltration of sensitive screenshot-borne data (Patent number: 12,067,493) These patents enhance Netskope's comprehensive intellectual property portfolio and solidify its competitive position in the industry. 

530
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Introducing Netskope SkopeAI for GenAI Hands-on Lab

We’re excited to invite you to our Netskope SkopeAI for GenAI Hands-On Lab. It provides a unique opportunity to learn how to detect new usage of GenAI apps such as ChatGPT, prevent sensitive data exposure using machine learning models, and further enhance your security posture using the Netskope One platform. The lab takes about 30 minutes to complete. Activate your lab today at https://www.netskope.com/company/events/introduction-to-skopeai-for-genai-hands-on-lab. 

1750
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Netskope Lands Two New AI/ML Patents

Netskope has been granted not one, but two brand new patents in the world of AI/ML - our expertise and commitment to delivering cutting-edge security solutions with AI/ML are on full display!"ML-based encrypted file classification for identifying encrypted data movement," Patent Number 11,947,682 “Image matching using deep learning image fingerprinting models and embeddings,” Patent Number 11,983,955The latest additions bring our total number of US patents related to AI/ML technology to an impressive 30. And we're just getting started!

760
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
New Patent and Blog Post on Train Your Own Classifier

Netskope has been awarded a new US patent (Patent Number 11,983,955) for our innovative image matching technology, specifically designed for image fingerprinting and classification. In our latest blog post, we delve into this cutting-edge technology behind Train Your Own Classifier (TYOC). 

511
S
Netskope Employee
aplaza
Netskope Employee
aplazaNetskope Employee
published in Artificial Intelligence and Machine Learning
NEW eBook—Securing GenAI for Dummies

Learn how to balance the innovative potential of GenAI while protecting your business. When approached correctly, effective data security enables businesses to leverage tools like ChatGPT and Google Gemini for competitive advantage. Conversely, neglecting the need for data security can lead to catastrophic consequences for your business.Read this ebook to learn how your organization can balance the potential of these innovative tools with robust data security practices.  📚 Get actionable insights with Securing Generative AI for Dummies eBook 📚

1420
aplaza
Netskope Employee
M
Netskope Employee
mgulledgeNetskope Employee
published in Artificial Intelligence and Machine Learning
Netskope Plugin for Microsoft Security CoPilotAI, ML, Skope AI

Microsoft has enhanced Security Copilot by preinstalling a set of plugins for their security services and frequently used websites. Additionally, you have the option to incorporate Netskope custom plugins, expanding Gen AI capabilities on your Netskope platform.RequirementsEnsure you have an active Microsoft Security CoPilot account and are able to login to: https://securitycopilot.microsoft.com/ For more information on Security CoPilot please visit: Get started with Microsoft Security Copilot Early Access ProgramCreate a local yaml file called NetskopeCoPilotSkill.yaml (filename can be anything). And paste the below in your yaml file: Descriptor: Name: Netskope Reporting for Threat and Data Protection DisplayName: Netskope Reporting API endpoints Description: The API plugin offers 6 skills that range from displaying Netskope Alerts and Events for Threat Hunting and Data Protection. SupportedAuthTypes: - ApiKey Authorization: Type: APIKey Key: Netskope-api-token Loca

17257
M
Netskope Employee
M
mchesmoNew Member
posted in Artificial Intelligence and Machine Learning
Preventing Virtual Assistants from recording meetings

Will Netskope block some of the virtual assistants like Otter.AI. I am trying to stop anyone from joining a MS Teams meeting and launching something like Otter.AI, regardless of if they are on a corporate device or a personal device.  

4021
S
Netskope Employee
H
HaxDrNew Member
posted in Artificial Intelligence and Machine Learning
Technical Support Documentation for AI Embedding

Hello!  I wanted to know if there is an easy way to get a copy of all the technical support docs from Netskope. Including API docs (which are currently only available at the Netskope admin console level). My goal is to create a vector database and ultimately teach an AI Agent Netskope. For practical purposes I'd like to see the extent by which I can extend and embed a model with data and how that would stack up to some of our in house support. Apart from the public facing knowledge base I'm looking for more documents on troubleshooting client side issues. Maybe even some documentation on how to spot errors in Netskope Debug Logs, etc...  Thanks for any and all support!-Hax

812
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Strengthening Cybersecurity: Harnessing the Power of AI/ML

In an era of escalating cyber threats and increasingly sophisticated attacks, organizations are facing an ever-growing challenge to safeguard their digital assets and sensitive information.Watch this demo with Netskope Chief Evangelist, Bob Gilbert, to hear how you can harness the power of AI/ML to strengthen your cybersecurity and defend against bad actors attempting to infiltrate your infrastructure.Demo Highlights:Learn how AI/ML is revolutionizing threat detection and data protection Discover cutting-edge AI/ML techniques for anomaly detection and behavior analysis See how artificial intelligence and machine learning are powering the future of data classification  

530
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Unveiling the Under-reported Aspects of AI

The conversation around AI/ML is everywhere, but it often leads to confusion and misconceptions. In the most recent episode of Netskope’s Security Visionaries podcast, we discussed the importance of AI transparency - a cornerstone for cultivating public trust and enabling individuals to make well-informed decisions about AI risks. We believe it's time for organizations to embrace openness and transparency about their AI models. For example, organizations should be prepared to answer: What's the data used to train a model? Does it include customer data? What inputs does the model rely on? What outputs does the model generate, and how are they used in the product? What are the limitations and accuracy of the model?   Let's work together to demystify the complex landscape of AI, fostering greater understanding and trust in this transformative technology.

350
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Gartner: 4 Ways Generative AI Will Impact CISOs and Their Teams

According to Gartner, “ChatGPT and large language models are the early signs of how generative AI (GenAI) will shape many business processes. Security and risk management leaders, specifically CISOs, and their teams need to secure how their organization builds and consumes GenAI, and navigate its impacts on cybersecurity.”   In addition, Gartner says that “The level of hype, scale and speed of ChatGPT adoption has raised end-user awareness of LLMs, leading to uncontrolled uses of LLM applications. It has also opened the floodgates to business experiments and a wave of AI-based startups promising unique value propositions from new LLM and GenAI applications. Many business and IT project teams have already launched GenAI initiatives, or will start soon.”   CISOs and security teams need to prepare for impacts from GenAI in four different areas according to Gartner: “Defend with” GenAI “Attacked by” GenAI Secure enterprise initiatives to “build” GenAI applications Manage and mon

360
yihualiao
Netskope Employee
farhan
Netskope Partner
farhanNetskope Partner
posted in Artificial Intelligence and Machine Learning
Netskope Client

How does the Netskope capture the data of User like email or used I'd when I install the agent via email invite or the mass script based what's was the intelligence behind it also what protocols used between ns client and Netskope cloud gateway (POP) please let me know this answer 

3513
S
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Introducing SkopeAI: Pioneering AI-Driven Data Security & Threat Protection Solutions!

I am proud to present to you the culmination of years of innovation and fruitful collaborations across multiple product teams at Netskope - the remarkable SkopeAI!SkopeAI stands as a testament to our commitment to excellence in the realm of AI-powered data security and threat protection solutions. We have harnessed the power of cutting-edge AI/ML technology to deliver industry-leading safeguards against modern-day security challenges.The launch of SkopeAI is not the end but rather a stepping stone in our AI journey. With an unwavering focus on staying at the forefront of AI and machine learning technology, we are determined to explore new frontiers, raise the bar higher, and enhance our security offerings.      

1740
yihualiao
Netskope Employee
V
vedNew Member
asked in Artificial Intelligence and Machine Learning
Generative AI

Today, I come to you seeking your valuable insights and suggestions on how we can enhance the security of our organization. Specifically, we aim to prevent users from uploading or sharing any source code through the platform Google Bard.To this end, we kindly request your expertise in brainstorming and proposing potential solutions to achieve our goal.In advance, I appreciate your help.

1442
V
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
What ChatGPT and Netskope’s Inline Phishing Detection Have in Common

  At Netskope, we have developed a deep learning-based Inline Phishing Detection Engine. Similar to generative pre-training of large language models, such as BERT and ChatGPT/GPT-4, we use a large number of web pages to train a HTML encoder and then use it to build the phishing classifier. The Inline Phishing Detection Engine has been generally available to all Intelligent SSE and Netskope Next Gen-SWG customers. In this blog post, we share some of the patient-zero and evasive phishing examples that the engine has detected.   Have you seen any phishing pages detected by the Inline Phishing Detection Engine in your environment? Please let us know if you have any feedback.   

380
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
AI and Deep Learning At Work: How to Know If Your Images Are Storing Sensitive Information

  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

630
yihualiao
Netskope Employee
amerdzan
Netskope Employee
amerdzanNetskope Employee
posted in Artificial Intelligence and Machine Learning
Linkedin Live Event - ChatGPT: Fortifying Data Security in the AI App-ocalypse

Join us on Linkedin Live on June 22 at 9:30am PDT to discuss how Generative AI SaaS applications, like ChatGPT, have revolutionized corporate workflows, but have also introduced significant data security risks.   Modern cloud-first businesses are grappling with unprecedented challenges as sensitive data becomes increasingly exposed to a new breed of applications. 📈 23% of employees access ChatGPT at least once a day, based on a recent Netskope study through Advanced Analytics, and this number is expected to grow rapidly. Join Netskope executive leaders for a lively discussion on: The sensational Generative AI phenomenon led by ChatGPT What Generative AI Apps can do: Endless possibilities How you can prevent data exposure, breaches and address compliance   Register Now 

280
amerdzan
Netskope Employee
Takashi_Ohmoto
Netskope Partner
Takashi_OhmotoNetskope Partner
asked in Artificial Intelligence and Machine Learning
Utilizing ChatGPT for Netskope URL Category Investigation

Dear Netskope administrators, let me share an idea about using ChatGPT as your assistant. Netskope has many URL categories, and here's a prompt to have ChatGPT respond to what categories are available.   Fill in the "Search criteria" part of the following prompt with the category you want to investigate, and by inputting it into ChatGPT, it will pick up the corresponding category for you.　Prerequisites: GPT4 is available, and the WebPilot plugin is enabled.　*Please note that this is a simple investigation, so if you are actually going to apply it, please carefully review the help page and set it accordingly.   ---ChatGPT Prompt---You are a security engineer. You are trying to restrict access to a website on a category basis. Please follow the Steps to pick the appropriate candidate. #Reference URLhttps://docs.netskope.com/en/category-definitions.html #Search criteriaSites where credit card input is expected, such as financial or e-commerce sites. #StepPick up category candida

1081
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Answering Key Questions About Embracing AI in Cybersecurity

The rise of generative AI tools such as ChatGPT has captured the attention of many people. In a recent blog post, we discussed the benefits, challenges, and potential risks of AI in the cybersecurity domain. We're curious: do you have any questions or concerns about AI? Feel free to share them with us! 

160
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
Improved DLP Image Classifiers

Machine learning-based image classification offers a fast and effective way to detect sensitive information within images, allowing for granular real-time DLP policy controls. Our DLP Classification Service accommodates an extensive range of image classifiers, such as passports, driver's licenses, SSNs, checks, payment cards, screenshots, whiteboards, and more. To improve its accuracy and provide better customer experience, we have retrained the classifiers for Release 103.   Significant changes were made to the image classifiers, including: A newer underlying model architecture with an 80% increase in the number of parameters High-quality labeled training data, including augmented images that are realistic for the image data we see in the cloud, to minimize false positives   According to our lab tests, most of the image classifiers show increased accuracy. If you have any questions or feedback about the image classifiers, please let us know.

2460
yihualiao
Netskope Employee
yihualiao
Netskope Employee
yihualiaoNetskope Employee
posted in Artificial Intelligence and Machine Learning
General Availability of Inline Phishing Detection Engine

Earlier this month, we enabled the inline AI-powered phishing detection engine in Netskope Threat Protection for all customers, significantly enhancing its capability to block phishing content in real time.    Phishing is one of the most common online security threats. At Netskope, we use cutting-edge deep learning techniques to learn the patterns of phishing websites. Similar to generative pre-training of large language models, such as BERT and GPT, we use a large number of web pages to train the HTML encoder and then use it to build the phishing classifier. We have been awarded three U.S. patents for our innovative approach to phishing detection.   We have been gradually rolling out the inline phishing detection engine. The engine has discovered a range of zero-day phishing attacks in customer traffic, including active phishing campaigns targeting Microsoft, Facebook, and so on.   How can you tell if a page was blocked by the inline phishing detection engine? &nbs

1130
yihualiao
Netskope Employee

Badge Winners

Show all badges

Not finding what you're looking for?

Don't be shy and let us know about your challenge.

Ask your question here!
Terms & ConditionsCookie settings