Operations

12/12/2016
11:55 AM
Rutrell Yasin
Rutrell Yasin
Slideshows
Connect Directly
Twitter
RSS
E-Mail
50%
50%

5 Things Security Pros Need To Know About Machine Learning

Experts share best practices for data integrity, pattern recognition and computing power to help enterprises get the most out of machine learning-based technology for cybersecurity.
Previous
1 of 6
Next

The concept of machine learning has been around for decades. Machine Learning (ML) is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed.

Industries and government agencies working with large amounts of data are using machine learning technology to glean insights from this data in real time. Financial institutions use the technology to identify investment opportunities and fraud. Utility companies use the technology to analyze sensor data to increase efficiency and save money. Healthcare practitioners are using the technology to identify trends that could improve diagnoses and patient treatment.

And, cybersecurity experts, inundated by reams of data generated by multiple information technology systems, security tools, networks, and other devices are deploying machine learning technology to detect and thwart internal and external cyber-attacks and threats.

“Machine learning helps humans be more efficient by [aggregating and analyzing] vast amounts of data. It’s not just the volume, but also the scope of data; more data at the same time and more facets of data at the same time,” says Sven Krasser, chief scientist at Crowdstrike, a developer of machine learning-based endpoint security tools.

“One of the big game changers is the emergence of cloud computing,” he says.  By using cloud-based infrastructures, security experts can aggregate more data from vast amounts of resources than ever before.” Traditional techniques where analysts sift through data in some manual fashion to generate rule sets doesn’t work well in today’s dynamically-changing threat environment, Krasser says.

System, sensors, and other networked-devices are generating so much data that it is increasingly difficult for human analysts to find those tidbits – the abnormalities and or patterns – that might give them the insights needed to identify an attack or potential threat, says Matt Wolff, chief data scientist with Cylance, a developer of endpoint security tools based on machine learning technology.

“So, machine learning is an excellent tool and the right approach to take when you have a data intensive problem that you want to solve,” Wolff says.

Industry executives and government agency officials are looking for ways to combat sophisticated attacks and relentless cyber adversaries while coping with a shortage of talented information security professionals. Machine learning-based security tools are yet another technology that they can add to their cyber arsenal.

DarkReading spoke with cybersecurity experts from CrowdStrike, Cylance, Darktrace, and IDC security researcher Peter Lindstrom to get a better sense of what organizations need to know about applying machine learning-based technology for cybersecurity in their organizations.

 

Rutrell Yasin has more than 30 years of experience writing about the application of information technology in business and government. View Full Bio

Previous
1 of 6
Next
Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
JonKim
50%
50%
JonKim,
User Rank: Author
12/15/2016 | 3:02:27 PM
Insightful
Insightful, thank you for sharing.
gopinathmohan861
50%
50%
gopinathmohan861,
User Rank: Apprentice
12/14/2016 | 10:11:16 AM
Machine Learning - Useful points
First of all, a big thanks for the article. The informations (5 security pros) mentioned in this article very useful. As AI and ML is going to rule future world, we need to consider these security pros.
Election Websites, Back-End Systems Most at Risk of Cyberattack in Midterms
Kelly Jackson Higgins, Executive Editor at Dark Reading,  8/14/2018
Intel Reveals New Spectre-Like Vulnerability
Curtis Franklin Jr., Senior Editor at Dark Reading,  8/15/2018
Australian Teen Hacked Apple Network
Dark Reading Staff 8/17/2018
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Current Issue
Flash Poll
The State of IT and Cybersecurity
The State of IT and Cybersecurity
IT and security are often viewed as different disciplines - and different departments. Find out what our survey data revealed, read the report today!
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2018-14981
PUBLISHED: 2018-08-17
Certain LG devices based on Android 6.0 through 8.1 have incorrect access control for SystemUI application intents. The LG ID is LVE-SMP-180005.
CVE-2018-14982
PUBLISHED: 2018-08-17
Certain LG devices based on Android 6.0 through 8.1 have incorrect access control in the GNSS application. The LG ID is LVE-SMP-180004.
CVE-2018-15482
PUBLISHED: 2018-08-17
Certain LG devices based on Android 6.0 through 8.1 have incorrect access control for MLT application intents. The LG ID is LVE-SMP-180006.
CVE-2018-15473
PUBLISHED: 2018-08-17
OpenSSH through 7.7 is prone to a user enumeration vulnerability due to not delaying bailout for an invalid authenticating user until after the packet containing the request has been fully parsed, related to auth2-gss.c, auth2-hostbased.c, and auth2-pubkey.c.
CVE-2018-15471
PUBLISHED: 2018-08-17
An issue was discovered in xenvif_set_hash_mapping in drivers/net/xen-netback/hash.c in the Linux kernel through 4.18.1, as used in Xen through 4.11.x and other products. The Linux netback driver allows frontends to control mapping of requests to request queues. When processing a request to set or c...