Contextual machine learning with Egress Prevent
Contextual machine learning
We use artificial intelligence and machine learning to understand users' behaviour in real time. This includes the context of who they communicate with and where they are located, the time they're communicating with these recipients, and the content contained within each email's body and attachments.
We can then dynamically detect any abnormal behaviour when employees either make mistakes or intentionally leak data.
Continuously understanding users' behavior
Bayesian inference models continuously update our risk assessments as more information about user roles becomes available, dynamically preventing emails being sent to the wrong person or with the wrong files attached.
Assessing relationship strength
We deploy graph databases to map out and interrogate the strength of a user's relationships in order to detect anomalous recipients and prevent misdirected emails.
Monitoring time patterns
Gaussian mixture models allow Egress Prevent to continuously learn about users' access time patterns, meaning we can spot unusual behavior and stop email data breaches.
Approximately 269 billion emails are sent every day. At that rate – and given the technology was developed decades ago – you would expect we’d have got to grips with it by now.
Gartner introduced its 'continuous adaptive risk and trust assessment' (CARTA) approach to security in 2017 as a response to the ever-changing threat landscape faced by digital businesses.
New report reveals that nearly three-quarters (71%) of AI detectors can’t tell if a phishing email has been written by a chatbot
Missed voice messages accounted for 18% of phishing attacks, making them the most phished topic of the year so far