Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Partner Perspectives  Connecting marketers to our tech communities.
SPONSORED BY
4/18/2018
09:00 AM
Joe Cosmano
Joe Cosmano
Partner Perspectives
Connect Directly
LinkedIn
RSS
50%
50%

How to Leverage Artificial Intelligence for Cybersecurity

AI and predictive analytics should be used to augment a company's security team, not replace it. Here's why.

Artificial intelligence (AI) and machine learning (ML) are two interrelated concepts that people across the tech landscape know hold important implications. While the benefits of these capabilities are many, experts in the field are also known to flaunt dire theories about them - from threats of dystopian futures ala The Matrix films to more tangible fears like wide-scale data breaches.

Machine learning falls under the broader AI umbrella as a technology that can enable computers to learn and adapt through experience, essentially, mirroring human cognition to recognize patterns. Successful examples of recent ML deployments include Google’s evolving search algorithms and Amazon’s product recommendations, along with the many "news feeds" that are common across social media.

But similar initiatives can have big dividends where cybersecurity is involved, especially in freeing up many of the more rote activities with which security staff are tasked. Predictive analytics and greater automation, for instance, are being employed via AI as an innovative means to fill the skills shortage that’s prevalent across the industry. This allows teams to off-load basic tasks in favor of high-priority or more technical initiatives.

Matching Human Capabilities at a Speed We Can’t touch

Any technology that can lessen the burden of an enterprise security team is extremely useful. Further to that, any time there is a defined data set that can be analyzed and categorized into a defined set of actions, AI will be successful. Some of the benefits that are already being enjoyed by security teams include things like enhanced behavioral analysis, email security and malware prevention.

For instance, businesses can use AI to help establish "known knowns" and "known unknowns" – that is, traffic behavior that follows an expected baseline of activity, and the traffic, users, or devices that appear anomalous by comparison. Even if an individual was given a single pane of glass to monitor all the traffic crossing the network perimeter, spotting anomalies would be nearly impossible given the number of users and devices that, on average, leverage contemporary enterprise networks.

The bottom line is that computers simply absorb information at a greater speed than humans while adhering to the same rules and protocols.

Tread Carefully at First

Of course, that isn’t to say there aren’t pitfalls to implementing AI and ML into a security workflow. It’s important to remember that AI and predictive analytics should be used to augment a company’s security team not replace it.

As was explained above, quality data sets will inform the success of an AI or ML program. If a business is collecting the wrong type of information from the get go, or is storing it incorrectly, AI and predictive analytics will be drawing conclusions based on incomplete or inaccurate information, leading to a reduction in performance.

Organizations achieve the greatest benefits from these technologies when they are used to free teams up from manual tasks in order to focus on higher-level problems that require "human" brain power to assess context and nuance. Those assessments can’t be passed onto computers – at least not yet.

It’s also important to expect that hackers will inevitably ramp up their use of AI in response to the new tactics being deployed by security teams. This underscores  the point that while cybersecurity tactics will change with team, threats will always be present, requiring dedicated human collateral to help businesses remain secure for years to come.

Joe Cosmano has over 15 years of leadership and hands-on technical experience in roles including Senior Systems and Network Engineer and cybersecurity expert. Prior to iboss, he held positions with Atlantic Net, as engineering director overseeing a large team of engineers and ... View Full Bio
Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
COVID-19: Latest Security News & Commentary
Dark Reading Staff 7/9/2020
Omdia Research Launches Page on Dark Reading
Tim Wilson, Editor in Chief, Dark Reading 7/9/2020
4 Security Tips as the July 15 Tax-Day Extension Draws Near
Shane Buckley, President & Chief Operating Officer, Gigamon,  7/10/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
Special Report: Computing's New Normal, a Dark Reading Perspective
This special report examines how IT security organizations have adapted to the "new normal" of computing and what the long-term effects will be. Read it and get a unique set of perspectives on issues ranging from new threats & vulnerabilities as a result of remote working to how enterprise security strategy will be affected long term.
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-15105
PUBLISHED: 2020-07-10
Django Two-Factor Authentication before 1.12, stores the user's password in clear text in the user session (base64-encoded). The password is stored in the session when the user submits their username and password, and is removed once they complete authentication by entering a two-factor authenticati...
CVE-2020-11061
PUBLISHED: 2020-07-10
In Bareos Director less than or equal to 16.2.10, 17.2.9, 18.2.8, and 19.2.7, a heap overflow allows a malicious client to corrupt the director's memory via oversized digest strings sent during initialization of a verify job. Disabling verify jobs mitigates the problem. This issue is also patched in...
CVE-2020-4042
PUBLISHED: 2020-07-10
Bareos before version 19.2.8 and earlier allows a malicious client to communicate with the director without knowledge of the shared secret if the director allows client initiated connection and connects to the client itself. The malicious client can replay the Bareos director's cram-md5 challenge to...
CVE-2020-11081
PUBLISHED: 2020-07-10
osquery before version 4.4.0 enables a priviledge escalation vulnerability. If a Window system is configured with a PATH that contains a user-writable directory then a local user may write a zlib1.dll DLL, which osquery will attempt to load. Since osquery runs with elevated privileges this enables l...
CVE-2020-6114
PUBLISHED: 2020-07-10
An exploitable SQL injection vulnerability exists in the Admin Reports functionality of Glacies IceHRM v26.6.0.OS (Commit bb274de1751ffb9d09482fd2538f9950a94c510a) . A specially crafted HTTP request can cause SQL injection. An attacker can make an authenticated HTTP request to trigger this vulnerabi...