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 //

bitdefender

12/12/2016
10:00 AM
Razvan Muresan
Razvan Muresan
Partner Perspectives
50%
50%

Machine-Learning Algorithms Improve Detection Time For Modern Threats

Artificial intelligence and machine learning are essential to combat a threat landscape that is larger and more sophisticated than ever.

Artificial intelligence and machine learning have become key drivers of innovation. Machine-learning algorithms significantly improve detection time for modern threats, as they can analyze large amounts of data significantly faster than any human could. If trained to accurately detect various types of malware behavior, machine-learning algorithms can have a high detection rate, even on new or unknown samples.

The merging of human ingenuity with the speed and relentless data analysis of machine learning significantly accelerates reactions against new malware, offering protection even from previously unknown samples – advanced persistent threats, zero-day attacks, and ransomware. However, it’s not always just a single machine-learning algorithm doing the detection. Detecting ransomware, for example, requires several algorithms, each specialized in detecting specific families with individual behaviors. This significantly increases the chances of detecting similar looking malware samples while reducing the number of false positives.

For its part, Bitdefender invests a quarter of its R&D budget in disruptive ideas, boosting its number of patents. From a total of 72 patents, Bitdefender has had 42 patents issued for core technologies in the past three years. In addition, 35 more are currently filed for examination. With almost 10% of Bitdefender’s patents pertaining to machine-learning algorithms for detecting malware and other online threats, deep learning and anomaly-based detection techniques play a vital role in proactively fighting new and unknown threats.

Bitdefender holds patents in all major areas of interest: machine-learning, antispam/anti-phishing/antifraud, antimalware, virtualization, BOX-functionality, and hardware design, among others. Bitdefender’s team of engineers and researchers reached the 600+ milestone this year. The company has been working on machine-learning algorithms since 2009, developing and training them to identify new and unknown threats. Artificial intelligence and machine learning are essential to combat a threat landscape that is larger and more sophisticated than ever.

Many of its patents hold the secrets to Bitdefender’s most recent innovations -- Bitdefender BOX, a solution that protects all of a user’s connected devices; and Hypervisor Introspection (HVI), a framework to secure virtualized environments from advanced targeted cyberattacks.

Bitdefender started integrating machine-learning technologies into its detection systems seven years ago, and its recent patents continue to help it achieve a high detection rate for new malware released in the wild.

Razvan, a security specialist at Bitdefender, is passionate about supporting SMEs in building communities and exchanging knowledge on entrepreneurship. A former business journalist, he enjoys taking innovative approaches to hot topics and believes that the massive amount of ... View Full Bio
Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
Navigating Security in the Cloud
Diya Jolly, Chief Product Officer, Okta,  12/4/2019
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: "The security team seem to be taking SiegeWare seriously" 
Current Issue
Navigating the Deluge of Security Data
In this Tech Digest, Dark Reading shares the experiences of some top security practitioners as they navigate volumes of security data. We examine some examples of how enterprises can cull this data to find the clues they need.
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2019-5098
PUBLISHED: 2019-12-05
An exploitable out-of-bounds read vulnerability exists in AMD ATIDXX64.DLL driver, version 26.20.13001.29010. A specially crafted pixel shader can cause out-of-bounds memory read. An attacker can provide a specially crafted shader file to trigger this vulnerability. This vulnerability can be trigger...
CVE-2012-1104
PUBLISHED: 2019-12-05
A Security Bypass vulnerability exists in the phpCAS 1.2.2 library from the jasig project due to the way proxying of services are managed.
CVE-2019-17387
PUBLISHED: 2019-12-05
An authentication flaw in the AVPNC_RP service in Aviatrix VPN Client through 2.2.10 allows an attacker to gain elevated privileges through arbitrary code execution on Windows, Linux, and macOS.
CVE-2019-17388
PUBLISHED: 2019-12-05
Weak file permissions applied to the Aviatrix VPN Client through 2.2.10 installation directory on Windows and Linux allow a local attacker to execute arbitrary code by gaining elevated privileges through file modifications.
CVE-2019-18381
PUBLISHED: 2019-12-05
Norton Password Manager, prior to 6.6.2.5, may be susceptible to a cross origin resource sharing (CORS) vulnerability, which is a type of issue that allows restricted resources on a web page to be requested from another domain outside the domain from which the first resource was served.