To optimally safeguard the sensitive nature of the data, we offer on site processing hardware to ensure no sensitive information ever leaves our customers organisation prior to anonymization.
Our approach to automatic anonymization combines both rule driven and machine learning technology. Specifically sequence based neural networks prove to be very effective for this purpose. In addition to extracting sensitive data, we also offer the option to add role based placeholders instead of the traditional “blackout” approach. This results in a much more readable text while still protecting any sensitive personal data.
Our solution is language independent. Currently it is used to extract sensitive information from Dutch and French legal documents, case law content and for English data analytics.
If you are interested in this application or its technology please contact us for a full demonstration of our anonymization technology.
