Skip Navigation LinksHome > News & Events > News > News Item

September 2011: Self-learning Network Attack Detection by TRIFENSE

Tuesday, September 27, 2011

September 2011: Self-learning Network Attack Detection by TRIFENSE

Due to the fast-paced exploitation of software vulnerabilities, today's network security technology is less effective in providing adequate protection against unknown, so-called "Zero-Day" attacks. As a result, professional hackers gain unauthorized access to high-value assets such as sensitive data or critical processes, thereby causing severe financial damages ($6.75 million per incident, on average) to individual organizations.

TRIFENSE GmbH, a Berlin/Brandenburg-based company, researches and develops self-learning solutions for ICT network security. TRIFENSE specializes in the development and integration of network security technology to protect high-risk computer networks against targeted, sophisticated hacking attacks. In contrast to state-of-the-art network security technology, the TRIFENSE attack detection module provides customized protection. Cutting-edge machine learning allows for reliable detection of known and unknown cyber attacks, the latter being deviations from data models learned over the inbound network packet payloads. The detection module currently operates at a processing speed of up to 1Gbps and can be installed on any Linux network gateway or integrated into third party network security products.

TRIFENSE originated as a result of two successful security research projects (“MIND” and “ReMIND”) at the Technical University Berlin and the Fraunhofer Institute. For more information, please click here.