June 22, 2016 By Larry Loeb 3 min read

The technologies behind cognitive systems have matured greatly in recent years, which has expanded the number and types of applications for the technology. One such initiative involves applying cognitive computing to cybersecurity.

Cognitive computing has five core capabilities. Looking at the ways these can be applied to the security arena may illuminate some interesting possibilities for IT professionals.

The Core Capabilities of Cognitive Systems

Cognitive technology creates a deeper human engagement. Cognitive security systems analyze all available structured and unstructured data to find what really matters — to a person or group. By being able to better understand an individual, users can gain insight into an attacker’s motives as well as the defender’s needs.

The pattern of how a system is used, based on actual operational patterns rather than just specifications, can point to areas that may be part of the attack surface that has gone unnoticed by an observer. Similarly, the attack patterns as a whole can lead to a better understanding of the true goals of the attacker instead of a simple list of targets.

Another capability these systems offer is the ability to scale and elevate the expertise brought to a problem. Cognitive computing can serve as a companion for professionals to enhance their performance. A wider range of experience and insight can be applied to the problem at hand through cognitive’s collection and analysis of data that might have otherwise been overlooked.

Products and services can be infused with cognitive systems as well. This means the augmentation of their capabilities to deliver uses that had not previously been imagined. Techniques currently used for cybersecurity purposes can expand their use cases when the relevant security tool capabilities are increased or amplified, for example.

When processes are integrated with cognitive capabilities, they can collect data from internal and external sources. These processes can then learn from unstructured data — something that has vexed other kinds of computing. That is huge, because unstructured data is what will drive the greater use of coincident information in automated decision-making.

It’s a great pool of currently unused information not found in current databases that should lead to a wider perspective of data relations.

How It’s Impacting Security

Cognitive can enhance exploration and discovery. Its core capabilities are exactly what the cybersecurity field needs.

Discovering and processing data allows cognitive to assist the professional who must make decisions about a given situation. It serves as a valuable tool to the decision-maker by searching remote areas for information and connections.

It could also make data collection a truly ongoing background process that is only accessed when needed. That way, you could have data that you didn’t even know you needed available because it had been automatically collected. Cognitive widens the data that can be surveyed, giving a greater breadth to the analysis that ensues.

IBM Security announced that, right now, 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 are all working on marrying cognitive computing and cybersecurity. They are also finding ways to best communicate analysis results to the people who need to know, increasing the odds that the results will actually get used.

Raw computing power by itself can be useless if it’s unfocused. Cognitive systems are focusing on identifying the most important aspects of security incidents and communicating those critical results. This characteristic — ease of use, even with complex queries — is part of the reason why cognitive will make its biggest security impact in the days to come.

Watch the video: Step up to the Cognitive Era with IBM Watson for Cyber Security

More from Artificial Intelligence

Cloud Threat Landscape Report: AI-generated attacks low for the cloud

2 min read - For the last couple of years, a lot of attention has been placed on the evolutionary state of artificial intelligence (AI) technology and its impact on cybersecurity. In many industries, the risks associated with AI-generated attacks are still present and concerning, especially with the global average of data breach costs increasing by 10% from last year.However, according to the most recent Cloud Threat Landscape Report released by IBM’s X-Force team, the near-term threat of an AI-generated attack targeting cloud computing…

Testing the limits of generative AI: How red teaming exposes vulnerabilities in AI models

4 min read - With generative artificial intelligence (gen AI) on the frontlines of information security, red teams play an essential role in identifying vulnerabilities that others can overlook.With the average cost of a data breach reaching an all-time high of $4.88 million in 2024, businesses need to know exactly where their vulnerabilities lie. Given the remarkable pace at which they’re adopting gen AI, there’s a good chance that some of those vulnerabilities lie in AI models themselves — or the data used to…

Security roundup: Top AI stories in 2024

3 min read - 2024 has been a banner year for artificial intelligence (AI). As enterprises ramp up adoption, however, malicious actors have been exploring new ways to compromise systems with intelligent attacks.With the AI landscape rapidly evolving, it's worth looking back before moving forward. Here are our top five AI security stories for 2024.Can you hear me now? Hackers hijack audio with AIAttackers can fake entire conversations using large language models (LLMs), voice cloning and speech-to-text software. This method is relatively easy to…

Topic updates

Get email updates and stay ahead of the latest threats to the security landscape, thought leadership and research.
Subscribe today