On any given day, cybersecurity analysts investigate ongoing incidents that could potentially impact their enterprise. They sift through mountains of data, false positives and ever-morphing malware and exploits to identify the few security events that are most likely to be problematic and require fast action.

To proactively mitigate their risk, they need to stay current on new types of threats and attack vectors documented in more than 1 million security bulletins, threat reports and news articles published each year.

Shifting Toward Cognitive Security

Advanced analytics and other software tools help security analysts detect anomalies and determine high-risk threats, but the volume of information combined with the rate and sophistication of attacks has made it nearly impossible for any single analyst to keep up.

Technology can help, but only to a point. Traditional security relies primarily on structured data that technology is capable of organizing and analyzing — but that only accounts for 20 percent of all the data out there. It’s the unstructured knowledge — the other approximately 80 percent of data delivered in natural language that analysts read and discuss all the time — that often proves most valuable in detecting and stopping threats before they cause harm.

Enter cognitive computing. Cognitive computing has the ability to tap into and make sense of security data that has previously been dark to an organization’s defenses, enabling security analysts to gain new insights and respond to threats with greater confidence at scale and speed. Cognitive systems are taught, not programmed, using the same types of unstructured information that security analysts rely on. Like an analyst, the system can learn as it goes, able to recognize terms and make connections between them, so it can understand questions and use reason to provide answers.

Our experts are currently teaching IBM’s cognitive system, Watson, the language of cybersecurity by annotating and feeding thousands of documents into the system to build up its corpus of knowledge. In turn, the system will be able to recognize and automate connections between millions of pieces of data at a scale and speed like never before.

Introducing Watson for Cyber Security

Today, we are announcing Watson for Cyber Security, which will consist of:

  • A new cloud-based version of IBM’s cognitive analytics solution using core Watson technology trained in the language of security to help analysts gain more precision, speed and accuracy in stopping cyberattacks.
  • A collaboration with universities in which students will be working with IBM experts to greatly expand the corpus of security data in the system. The universities include: California State Polytechnic University, Pomona; Pennsylvania State University; Massachusetts Institute of Technology; New York University; the University of Maryland, Baltimore County; the University of New Brunswick; the University of Ottawa; and the University of Waterloo.

The more Watson works with actual users, such as clients and business partners, the more it will understand the context of the information it’s learning. That means it will not only be able to provide more precise answers, but it will also make connections between data points that a security analyst may never have considered.

Cognitive computing can help us keep up with the rate and pace of the threat landscape, especially in the face of a significant cybersecurity skills shortage. Watson for Cyber Security won’t replace security analysts, but rather will augment their knowledge so they can more effectively investigate and respond to threats. What would take a security analyst days or weeks to investigate, Watson will be able to do in minutes or hours.


A Glimpse Into the Future

Imagine a typical day for security analysts using Watson for Cyber Security. They would come into the office and, with their trusted Watson security adviser, could quickly and accurately analyze graphically representations of emerging threats that might impact their organization.

Since Watson will have read the latest reports and applied them to events in the organization’s environment, it can respond to natural-language questions. Security professionals will be able to be more proactive, spending less time on the mundane and more on the important work of stopping attacks and protecting their enterprise.

Cybercrime isn’t going away anytime soon. Criminals are getting stronger and smarter, making it increasingly difficult for the good guys to stay ahead. Once available in the marketplace, Watson for Cyber Security will be able to help give the good guys the advantage.

Learn More

More from Intelligence & Analytics

RansomExx Upgrades to Rust

IBM Security X-Force Threat Researchers have discovered a new variant of the RansomExx ransomware that has been rewritten in the Rust programming language, joining a growing trend of ransomware developers switching to the language. Malware written in Rust often benefits from lower AV detection rates (compared to those written in more common languages) and this may have been the primary reason to use the language. For example, the sample analyzed in this report was not detected as malicious in the…

Moving at the Speed of Business — Challenging Our Assumptions About Cybersecurity

The traditional narrative for cybersecurity has been about limited visibility and operational constraints — not business opportunities. These conversations are grounded in various assumptions, such as limited budgets, scarce resources, skills being at a premium, the attack surface growing, and increased complexity. For years, conventional thinking has been that cybersecurity costs a lot, takes a long time, and is more of a cost center than an enabler of growth. In our upcoming paper, Prosper in the Cyber Economy, published by…

Overcoming Distrust in Information Sharing: What More is There to Do?

As cyber threats increase in frequency and intensity worldwide, it has never been more crucial for governments and private organizations to work together to identify, analyze and combat attacks. Yet while the federal government has strongly supported this model of private-public information sharing, the reality is less than impressive. Many companies feel that intel sharing is too one-sided, as businesses share as much threat intel as governments want but receive very little in return. The question is, have government entities…

Tackling Today’s Attacks and Preparing for Tomorrow’s Threats: A Leader in 2022 Gartner® Magic Quadrant™ for SIEM

Get the latest on IBM Security QRadar SIEM, recognized as a Leader in the 2022 Gartner Magic Quadrant. As I talk to security leaders across the globe, four main themes teams constantly struggle to keep up with are: The ever-evolving and increasing threat landscape Access to and retaining skilled security analysts Learning and managing increasingly complex IT environments and subsequent security tooling The ability to act on the insights from their security tools including security information and event management software…