The benefits of machine learning and UEBA

1 May 2019 Information Security

The cost of cybercrime is rapidly outpacing our ability to keep up. While Gartner predicts worldwide spending on information security to reach $124 billion this year, security researchers also estimate that the cost of cybercrime will exceed $2 trillion in that same time, outpacing security spending by over 16 times.

Doros Hadjizenonos
Doros Hadjizenonos

The vast majority of malware simply targets known vulnerabilities, while botnets now remain undetected inside targeted organisations for an average of nearly 12 days. The problem in many cases is one of resources. The rapid expansion of the attack surface through digital transformation and the unprecedented adoption of BYOD and IoT devices, combined with the growing sophistication of attacks and widening security skills gap has overwhelmed many security teams.

To address this challenge, organisations are turning to things like machine learning (ML) to fill their security gaps. The question is whether machine learning can add new value to the realm of cybersecurity?

Detection and prevention

Most organisations are currently operating with the standard cybersecurity kit. Their wiring closets are filled with devices that tout security policies that vendors claim can detect and prevent the latest threats by way of signature-based detection, canned policies, or even user-defined configurations. Sensors in this category – and experts estimate that organisations may have solutions from as many as 70 different security vendors inside their network – include firewalls, data loss prevention (DLP) systems, intrusion prevention systems (IPS) and web content filters (WCF).

In addition, many of these devices operate in complete isolation, unable to share or correlate threat intelligence or respond to threats in any sort of cohesive or coordinated strategy. As a result, even monitoring these appliances requires an extra layer of sensors – along with additional security team members to manage them and hand-correlate their syslog events.

Machine learning - what it is

Machine learning (ML) is a subset of AI. AI and ML can augment our human capabilities by allowing us to carve through large datasets and spot patterns of behaviour, or signals in the noise, that would be all but impossible for humans to do. This provides a force multiple, enabling your existing human talent to spot unusual behaviour automated behavioural analytics, or UEBA (user entity behaviour analytics) tools. Mundane tasks can also be automated with ML, allowing scarce cybersecurity personnel resources to focus on higher value tasks.

UEBA: providing the big picture

ML and AI are based on big data, and their efficiency and accuracy gets better the more data you throw at them. What’s important, however, is that you are collecting the right data. That’s where UEBA systems come in. Combining accurate and essential user behavioural data with machine learning allows you to more accurately monitor your users on an endpoint-by-endpoint basis, providing you with deep visibility into what they get up to on a regular basis.

Once a baseline of normal behaviour is established, any time a user does something that the UEBA system considers outside of normal, the cybersecurity ops team is alerted. If a user’s legitimate activity is flagged as anomalous, which can happen frequently during the initial learning stages, your analysts can simply tag the activity as routine and the UEBA system’s machine learning integrates that data and goes back to business as usual. As machine learning reduces such false positives, any time a user strays from normal behaviour those notifications become more urgent.

The benefits of combining ML and UEBA

Using machine learning alongside user behaviour data provides a level of security proactivity that is not possible when relying on traditional signature-based prevention and detection systems. This is due to the fact that you’re able to detect subtle changes in behaviour that’s tough to do with signatures. It’s simply not possible to configure a system with every single rule permutation to detect all attacks.

Detecting low-level reconnaissance activity using UEBA and machine learning is far more likely to set off your Spidey-senses than combining machine learning with traditional signature-based detection measures. This provides a huge advantage, making it a lot harder for attackers to circumvent control by flying under any rules-based radar.

The benefits to using a UEBA security solution built on a machine learning platform are many. As their ability to baseline network activity is refined, they can not only detect anomalous changes in behaviour, but that information can also enable proactivity by identifying and preventing certain behaviours before the occur. And since machine learning solutions generally provide their own care and feeding, minus a few tweaks here and there, overhead to manage them is reduced to a minimum.

But perhaps most importantly, machine learning is coming on the scene at a very opportune time because the number of analysts required to sift through data by hand to identify threats is rapidly outpacing the number of professionals currently available. By removing the human from a task that they’re not especially suited to, they are free to focus on those areas where they can add value, such as further developing your cybersecurity practice.





Share this article:
Share via emailShare via LinkedInPrint this page



Further reading:

Want effective Attack Surface Management? Think like an attacker.
Information Security
Effective ASM requires companies to think like attackers, anticipate risks, and act decisively to reduce exposure by knowing their environment, deploying a structured approach, leveraging capable tools, and addressing both internal and external risks.

Read more...
The growing role of hybrid backup
Infrastructure Information Security
As Africa’s digital economy rapidly grows, businesses across the continent are facing the challenge of securing data in an environment characterised by evolving cyberthreats, unreliable connectivity and diverse regulatory frameworks.

Read more...
POPIA non-compliance puts municipalities at risk
Information Security Government and Parastatal (Industry)
Digital responsibility must go beyond POPIA compliance to recognising that privacy and service delivery are fundamentally linked. Despite this, only 51 out of 257 municipalities submitted their mandatory data protection and access to information reports in 2024.

Read more...
Choicejacking bypasses smartphone charging security
News & Events Information Security
Choicejacking is a new cyberthreat that bypasses smartphone charging security defences to confirm, without the victim’s input or consent, that the victim wishes to connect in data-transfer mode.

Read more...
Most wanted malware
News & Events Information Security
Check Point Software Technologies unveiled its Global Threat Index for June 2025, highlighting a surge in new and evolving threats. Eight African countries are among the most targeted as malware leaders AsyncRAT and FakeUpdates expand.

Read more...
Welcome to the new cyber battleground
Information Security
The Iran-Israel conflict is rapidly redefining modern warfare, pushing the boundaries of cyber capabilities and creating a new, borderless digital battlefield. Fortinet’s CISO, Dr Carl Windsor, offers a critical, in-depth analysis of the escalating tactics and global implications in his latest report.

Read more...
African industries may overestimate cyber defences
Information Security
A significant perception gap exists in security awareness training: 68% of leaders believe training is tailored to roles, yet only a third of employees feel adequately trained. Many organisations only conduct annual or biannual generic training that may not effectively change behaviour.

Read more...
SMARTpod talks to Sophos and Phishield
SMART Security Solutions Technews Publishing Sophos Videos Information Security News & Events
SMARTpod recently spoke with Pieter Nel, Sales Director for SADC at Sophos, and Sarel Lamprecht, MD at Phishield, about ransomware and their new cyber insurance partnership.

Read more...
Highest increase in global cyberattacks in two years
Information Security News & Events
Check Point Global Research released new data on Q2 2024 cyber-attack trends, noting a 30% global increase in Q2 2024, with Africa experiencing the highest average weekly per organisation.

Read more...
Corporate and academic teams can register for Kaspersky contest
Kaspersky News & Events Information Security
Kaspersky has announced the registration opening for its new Kaspersky{CTF} (Capture the Flag) competition, inviting academic and corporate teams from around the globe to compete in a battle of skill, strategy and innovation.

Read more...










While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.




© Technews Publishing (Pty) Ltd. | All Rights Reserved.