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.
Julian Assange Arrested in London
Dark Reading Staff 4/11/2019
Tips for the Aftermath of a Cyberattack
Kelly Sheridan, Staff Editor, Dark Reading,  4/17/2019
The Single Cybersecurity Question Every CISO Should Ask
Arif Kareem, CEO, ExtraHop,  4/15/2019
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
5 Emerging Cyber Threats to Watch for in 2019
Online attackers are constantly developing new, innovative ways to break into the enterprise. This Dark Reading Tech Digest gives an in-depth look at five emerging attack trends and exploits your security team should look out for, along with helpful recommendations on how you can prevent your organization from falling victim.
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2019-11320
PUBLISHED: 2019-04-18
In Motorola CX2 1.01 and M2 1.01, users can access the router's /priv_mgt.html web page to launch telnetd, as demonstrated by the 192.168.51.1 address.
CVE-2019-11321
PUBLISHED: 2019-04-18
An issue was discovered in Motorola CX2 1.01 and M2 1.01. The router opens TCP port 8010. Users can send hnap requests to this port without authentication to obtain information such as the MAC addresses of connected client devices.
CVE-2019-11322
PUBLISHED: 2019-04-18
An issue was discovered in Motorola CX2 1.01 and M2 1.01. There is a command injection in the function startRmtAssist in hnap, which leads to remote code execution via shell metacharacters in a JSON value.
CVE-2019-8999
PUBLISHED: 2019-04-18
An XML External Entity vulnerability in the UEM Core of BlackBerry UEM version(s) earlier than 12.10.1a could allow an attacker to potentially gain read access to files on any system reachable by the UEM service account.
CVE-2018-17168
PUBLISHED: 2019-04-18
PrinterOn Enterprise 4.1.4 contains multiple Cross Site Request Forgery (CSRF) vulnerabilities in the Administration page. For example, an administrator, by following a link, can be tricked into making unwanted changes to a printer (Disable, Approve, etc).