Gurucul Risk Analytics 7.0 Uses Machine Learning Models for Real-Time Threat Detection
If you’re following Gurucul on social media, and staying up-to-date on our latest press releases, you will know about the release of the newest version of our risk analytics platform. Gurucul Risk Analytics (GRA) 7.0 provides real-time anomaly and risk detection across enterprise and cloud platforms/applications, networks, mobile endpoints, IoT devices, medical devices, and more. Additionally, this new version includes a vast library of machine learning models for threat detection. GRA goes beyond SIEM capabilities by using advanced behavior-based security and fraud analytics technology to detect and prevent external and insider threats in real-time.
No Such Thing as Too Many Machine Learning Models
Gurucul’s machine learning library, pre-packed with over 1,000 models, enables organization to implement model-driven security. As a result, this continuous, model-driven process automates the response to risky activity. It also improves the end user experience. For example, doing away with passwords because the machine learning model can make an in-the-moment decision about a users’ confirmed or unconfirmed identity. Another thing you should know about GRA is that all the existing models can be customized or built using Gurucul STUDIO.
We haven’t named every single machine learning model we offer (that would take a while), but we do have names and use cases for a few. Learn how Gurucul’s behavior based security analytics implements these models for advanced threat detection and prevention by reading the blog posts below.
- Detect Merchant Fraud with “Outlier Categorical Model”
- Protect Classified Information with “Identity Classification”
- Streamline Investigations with “Link Analysis”
- Identify Good UEBA Data with “Feature Analysis”
- Thwart Money Laundering with “Dimensionality Reduction”
- Prevent Fraud with “Rare and Volume Based Analytics
- Stop Fileless Malware with “Abnormal Powershell Command Execution”
- Identify Outlier Access with “Clustering and K-Means”
- Detect Privileged Access Abuse with “Linear Regression”
- Dynamic Provisioning: “Workflow Classification Regression Tree”
- Detect Host Compromise with “Domains Generated Algorithmically”
- Pinpoint Departing Users with “Predictive Flight Risk”
- Discover Privileged Accounts with “Entitlement Classification”
- Detect Insider Threats with “Email Fuzzy Logic”
Gurucul Risk Analytics 7.0 Goes Beyond SIEM at RSA Conference 2019
If you’re using a SIEM, then we suggest you consider a real security analytics tool. With a SIEM solution, you’re writing rules and queries to detect what you already know to look for. But GRA uses machines learning on big data to alert you on what you don’t know to look for. The best part? Well, there’s many… but we’re pretty sure not having to pay for data is a BIG reason why organizations looking for a security analytics solution go with Gurucul.
Gurucul will be demonstrating this new version of its risk analytics platform at RSA Conference in San Francisco March 4-7. Stop by booth #2027 in the South Expo Hall to meet with Gurucul executives and data scientists. So, come with your most puzzling security program and threat detection challenges. Then we will show you how Gurucul Risk Analytics can mitigate those issues.
Lastly, if you are attending RSA Conference, we hope you will attend our short presentation: A Security Evolution, which will be presented every 20 minutes at the booth. Learn how Gurucul takes security beyond SIEM to deliver behavior based security analytics.
Not going to RSA? No worries – contact us today to request a demo.
The post Gurucul Risk Analytics 7.0 Uses Machine Learning Models for Real-Time Threat Detection appeared first on Gurucul.
*** This is a Security Bloggers Network syndicated blog from Blog – Gurucul authored by Talia Landman. Read the original post at: https://gurucul.com/blog/gurucul-risk-analytics-machine-learning-threat-detection
