Threat Intelligence

02:00 PM
Connect Directly

IBM Brings Watson Cognitive Computing To The SOC

Technology known for a Jeopardy stunt six years ago is now powering question answering within IBM Security's QRadar system.

IBM hopes to elevate artificial intelligence and cognitive computing way beyond party tricks and game show supremacy and as a part of that push, Big Blue picked cybersecurity as a prime market to explore the possibilities. Today, IBM announced that it's officially marrying up its cybersecurity portfolio with the vaunted Watson questioning answering system.

Known best for its performance as a "contestant" on the game show Jeopardy in 2011, Watson was engineered to ingest vast quantities of data on any given subject in order to receive and answer questions in a conversational fashion. A system specifically developed to tackle Jeopardy, this cognitive technology uses natural language processing and machine learning to sift through data sources, synthesize information contained within, find and rank hypotheses and come up with a precise answer to the user's questions.

In the ensuing six years since Watson's success in winning a $1 million first prize in Jeopardy against two human champions, IBM has not only refined Watson's engine but al so been on the look out for ideal business cases to put the technology to use. The firm has achieved early successes in medical decisioning technologies, tracking customer and social media sentiment, and analyzing satellite and municipal data to track water use for drought mitigation.

With the growing problem of alert fatigue and a shortage of skilled security analysts, the industry seemed like it was crying out for Watson's help. The idea is to pair security operations center (SOC) technologies with Watson's processing capabilities so that analysts can ask the system questions about their data and existing threat posture, and receive meaningful advice on further action.  

The announcement follows a year of learning for Watson, which for the past 12 months has been trained on the language of cybersecurity, ingesting over 1 million security documents in the process.

"We've been teaching it for basically about a year, and it’s learned a lot along the way and it’s got a lot smarter along the way. It can read a ton more than it ever could before," says Caleb Barlow, vice president of threat intelligence for IBM Security. "And now we're at the point where it’s kind of graduated college and it’s time to go get that first real job."

According to Barlow, IBM's intent is to take the strain off of teams who can't afford or find enough skilled operators to manage the volume of advanced threats that barrage enterprise networks. Not only will they be able to make faster decisions, but they should be able to do it with more complete data. For instance, he referenced one competition a customer created during beta where they pit a team of experienced analysts against a team of junior analysts armed with Watson. They were given a certain security incident and an hour to look into it. The skilled analysts were able to confirm that attackers were testing the  network with an attempt at brute force password attacks, but believed that nothing further had occurred. Meanwhile, the Watson team identified those attempts but also were able to connect it with a form of malware, and then identify that the malware was actually on the network tied to the same threat actor.

"So, as you can imagine, that’s a very exciting find for that security team," Barlow says, "because now they know exactly how to go to address it, and they know, 'Wait a minute, this isn’t somebody who’s knocking at the door, this entity’s actually already in the door; they're just trying to get more access.'"

The centerpiece of what IBM calls its Cognitive SOC paltform will be IBM QRadar Watson Advisor, which brings together Watson with its QRadar security intelligence platform. The natural language processing capabilities will sift through a variety of security sources, including security blogs, websites, research papers and combine that with threat intelligence and security data from users' QRadar systems.  IBM will also be bringing cognitive tools to its global X-Force Command Center network and has rolled out a Watson-powered chat bot for IBM Managed Security Services customers.  Additionally, the company has a new project codenamed Havyn, which plans to also add voice-activated capabilities so that analysts can query the system by speaking plain-language questions aloud.

Related Content:



Ericka Chickowski specializes in coverage of information technology and business innovation. She has focused on information security for the better part of a decade and regularly writes about the security industry as a contributor to Dark Reading.  View Full Bio

Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
User Rank: Apprentice
9/5/2017 | 7:55:00 AM
Thoughts on Watson
Very interesting. Watson was revolutionary when it won Jeopardy. I remember thinking, Wow this thing is going to only grow and become more advanced, and be able to help companies all over the world become way more efficient. Looks like now that is finally starting to take place, in security measures. Pretty cool stuff.
User Rank: Apprentice
2/13/2017 | 5:43:15 PM
Watson focused on Information Security SOC Work
Very insteresting read.  I find many organizations utilizing "Big Data", "Neural Networks", and "Machine Learning" to be little more than signatures based on behaviors.  It will be interesting to see how this competes with Cylance in identifying positive and negative payloads.
Who Does What in Cybersecurity at the C-Level
Steve Zurier, Freelance Writer,  3/16/2018
Disappearing Act: Dark Reading Caption Contest Winners
Marilyn Cohodas, Community Editor, Dark Reading,  3/12/2018
Microsoft Report Details Different Forms of Cryptominers
Kelly Sheridan, Staff Editor, Dark Reading,  3/13/2018
Register for Dark Reading Newsletters
White Papers
Current Issue
How to Cope with the IT Security Skills Shortage
Most enterprises don't have all the in-house skills they need to meet the rising threat from online attackers. Here are some tips on ways to beat the shortage.
Flash Poll
[Strategic Security Report] Navigating the Threat Intelligence Maze
[Strategic Security Report] Navigating the Threat Intelligence Maze
Most enterprises are using threat intel services, but many are still figuring out how to use the data they're collecting. In this Dark Reading survey we give you a look at what they're doing today - and where they hope to go.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
Published: 2017-05-09
NScript in mpengine in Microsoft Malware Protection Engine with Engine Version before 1.1.13704.0, as used in Windows Defender and other products, allows remote attackers to execute arbitrary code or cause a denial of service (type confusion and application crash) via crafted JavaScript code within ...

Published: 2017-05-08
unixsocket.c in lxterminal through 0.3.0 insecurely uses /tmp for a socket file, allowing a local user to cause a denial of service (preventing terminal launch), or possibly have other impact (bypassing terminal access control).

Published: 2017-05-08
A privilege escalation vulnerability in Brocade Fibre Channel SAN products running Brocade Fabric OS (FOS) releases earlier than v7.4.1d and v8.0.1b could allow an authenticated attacker to elevate the privileges of user accounts accessing the system via command line interface. With affected version...

Published: 2017-05-08
Improper checks for unusual or exceptional conditions in Brocade NetIron 05.8.00 and later releases up to and including 06.1.00, when the Management Module is continuously scanned on port 22, may allow attackers to cause a denial of service (crash and reload) of the management module.

Published: 2017-05-08
Nextcloud Server before 11.0.3 is vulnerable to an inadequate escaping leading to a XSS vulnerability in the search module. To be exploitable a user has to write or paste malicious content into the search dialogue.