At Wandera, we’re taking full advantage of the opportunities offered by the enticing world of machine learning. We’ve invested significant resources into our data science team, and after more than a year of development, we’ve released our threat detection engine MI:RIAM.
MI:RIAM is our mobile intelligence, comprised of a number of advanced data analysis techniques and algorithms. As a collection of technologies spanning the entire machine learning spectrum, MI:RIAM is among the most powerful security engines ever created.
What She Does
We built MI:RIAM to solve some of the biggest challenges in security. Wandera provides security solutions to organizations looking to protect their corporate-owned devices from threats and to manage the risk involved in enterprise mobility.
To deliver this service effectively, there is a clear need for total visibility into how devices are being used. Billions of data points are generated every single day, and analyzing these to identify threats and achieve this kind of visibility is a colossal undertaking.
That’s why we’ve turned to machine learning to augment these security features, enhancing our ability to detect and block the growing number of risks posed to businesses. Here are just a few of the key values MI:RIAM provides:
- Zero-day threat detection: MI:RIAM uses Wandera’s global footprint to identify patterns of risk. This enables Wandera’s mobile security service to identify new leaks and highlight previously unknown vulnerabilities.
- Anomaly identification: Trained on the standard operating procedure of devices, apps, Wi-Fi access points and user groups, MI:RIAM builds a baseline understanding of behaviour, then seeks out anomalies.
- Risky app discovery: MI:RIAM continuously analyzes apps that are installed and the network traffic they generate. This higher-level analysis allows MI:RIAM to identify risky apps before they put the organization at risk.
- Instant reactions: MI:RIAM makes informed, intelligent decisions about the security events she encounters, enabling Wandera to respond by blocking filtering and altering in a heartbeat.
- Data usage optimization: MI:RIAM continually compares company usage patterns and policy to optimize data connections on the fly.
- Infrastructure risk assessments: MI:RIAM uncovers malicious infrastructures, as well as conducts analysis of potentially problematic regions or into the extent of breached devices.
How She Works
Of course, just like Alexa, Siri or Watson, MI:RIAM isn’t a single entity that operates independently of anything else. She’s made up of a number of different technologies, which collectively help to power many of the features available in Wandera.
“With the power of MI:RIAM by Wandera working alongside VMware AirWatch, you get the combined power of multi-level visibility along with a sophisticated array of tools to manage your devices.”
MI:RIAM is uniquely positioned to deliver innovative and market-leading mobile intelligence. With hundreds of thousands of devices accessible in its network, MI:RIAM has access to a vast archive of mobile data, far larger than any other comparable technology. Leading machine learning research has shown that as the volume of training data increases, the accuracy of findings becomes far more accurate and consistent.
Wandera’s data set is not only substantial but also operates in real time. MI:RIAM can process data in the same instant it is generated, crucially keeping devices protected the moment a threat occurs and not a day later.
Furthermore, this data set is more diverse than any other mobile security technology on the market, drawing data from the network (the data flowing in and out of the device), from the applications installed on the device, from the supporting infrastructure and from the device itself. These perspectives provide an unprecedented variety of data for MI:RIAM to analyze, helping produce accurate, timely and original insights.
The actual technologies that underlie the analysis powering MI:RIAM are comprised of a variety of different machine learning techniques. Naturally, in the secretive world of high-tech innovation, we’ve got no plans to publish the inner workings of MI:RIAM, but here is a selection of some of the techniques that have been integrated into the product.
- Neural networks: A very broad class of machine learning algorithms loosely based on imitating a biological brain. Responsible for several recent breakthroughs, especially in image processing and language translation.
- Clustering: Attempting to divide a set of samples into different groups such that samples in the same group are more similar to each other than samples in the other groups.
- Support vector machine: A binary classification algorithm that works by finding the dividing line between two types of samples.
- Anomaly detection: A broad class of problems in machine learning and statistics about finding samples that are different from the norm. This can include unusual periods in time, users, apps, etc.
- Predictive analytics: The field of making predictions about the future based on current data by whatever method—be that machine learning algorithms or statistics.
- Markov models: A predictive model in which a system can be in one of a certain number of states and the probability of future states depends only on the current state.
Machine learning is a technology showing no signs of slowing down. Working silently in the background, data science is swiftly transforming how the world’s most innovative businesses are solving an array of different problems.
At Wandera, we’re excited about the many ways MI:RIAM is enhancing and augmenting our understanding of the latest threats and insights. The inception of MI:RIAM is just the beginning. Her capabilities will be optimized over time, iteratively improving in her ability to spot new attacks, identify vulnerabilities and surface meaningful insights.
With the power of MI:RIAM by Wandera working alongside VMware AirWatch, you get the combined power of multi-level visibility along with a sophisticated array of tools to manage your devices. This means new insights on the security and status of every device can be surfaced at the device, application or data level. These insights can then be responded to using the functionality of either platform.
To find out more about what MI:RIAM from Wandera and AirWatch can do for your organization, request a demo to speak to one of our mobility experts.
Learn How Wandera & AirWatch Work Together
- Wandera & AirWatch Joint Case Study on Totaljobs Group
- How This Company Blocks Over 1,000 Mobile Security Threats Every Month
- Wandera Secure Mobile Gateway in the VMware Workspace ONE Marketplace
This post is written by Michelle Base-Bursey, product and partner marketing manager at Wandera.