Darktrace is the world’s leading machine learning company for cyber security.
Created by mathematicians from the University of Cambridge, Darktrace’s Enterprise Immune System uses AI algorithms that mimic the human immune system to defend enterprise networks of all types and sizes.
Our self-learning approach is the first non-consumer application of machine learning to work at scale, across all network types, from physical, virtualized, and cloud, through to IoT and industrial control systems.
By applying its unique, unsupervised machine learning, Darktrace has identified 53,000 previously unknown threats in over 3,750 networks, including zero-days, insider threats and subtle, stealthy attacks.
The founders of Darktrace include senior members of the UK government’s cyber community from MI5 and GCHQ, and Lord Evans, former Director-General of MI5, sits on the advisory board.
Our expert team have had experience on the frontline of cyber defense, and have been responsible for the protection of critical national assets – people, public services, and core intellectual property – from some of the most insidious threats in operation, including both sophisticated insider attacks and large-scale, state sponsored espionage groups. Darktrace’s team has now expanded to include experts from intelligence communities globally, such as the NSA and CIA, with backgrounds ranging from threat analysis to senior intelligence positions.
Darktrace’s Enterprise Immune System’s flagship threat detection and defense capability are based on unsupervised machine learning and probabilistic mathematics.
Powered by advanced machine learning, together with a new branch of Bayesian probability theory, Darktrace is the only self-learning cyber defense technology proven to work at scale. It is capable of detecting cyber-threats and anomalous behaviors that bypass traditional security tools, without prior knowledge of specific threats, or using rules or signatures.
Darktrace works by creating unique behavioral models for every user and device across the enterprise, and analyzing the relationships between them.
Leveraging its unique machine learning algorithms, Darktrace forms an evolving understanding of an organization’s ‘pattern of life’ (or ‘self’), spotting very subtle changes in behaviors, as they occur. These behavioral changes are correlated and filtered, in order to detect emerging threats and anomalies.
Darktrace is easily and rapidly installed into the heart of the network, typically at a SPAN or TAP port. It passively monitors raw network data – including cloud interactions – in real time, without disrupting business operations. Darktrace then provides instant visibility into all digital activity, notifying of in-progress attacks or emerging anomalies.
Our self-learning approach is the first non-consumer application of machine learning to work at scale, across all network types, from physical, virtualized, and cloud, through to IoT and industrial control systems. The typical installation time is one hour.
- Adaptive – evolves with your organization
- Self-learning – constantly refines its understanding of normal
- Probabilistic – works out likelihood of serious threat
- Real-time – spots threats as they emerge
- Works from day one – delivers instant value
- Low false positives – correlation of weak indicators
- Data agnostic – ingests all data sources
- Highly accurate – models human, device and enterprise behavior
- Installs in 1 hour – no configuration