D.A.T.E is a customizable data protection and personally identifiable information (PII) solution. It masks any personal or sensitive texts by removing specific personal data and replace it with synthetic data or asterisks.

It is fully context-aware for unstructured text in documents and images (supported formats: doc, docx, xls, xlsx, jpg, tlf, png, pdf). We use Natural Language Processing (NLP) to identify entities by context. After we identify any sensitive entities—names, locations, phone numbers, credit card numbers, etc.—we are able to anonymize it in many ways, such as hashing or encrypting.

In order to comply with the GDPR and other data protection legislations, companies need to have a privacy protection policy firmly in place. Among the activities involved in protecting personal data is data anonymization and data pseudonymization.

In the process of anonymization, any data that could potentially identify a specific individual is removed from data sets, which ensures anonymity and is essential for preservation of personal privacy, data privacy and protection, and information security.

Pseudonymization is a de-identification procedure by which personally identifiable information fields within a data record are replaced by one or more artificial identifiers, or pseudonyms. Pseudonymized data can be restored to its original state with the addition of information which allows individuals to be re-identified. In contrast, anonymization is intended to prevent re-identification of individuals within the dataset.

The main process of pseudonymization and anonymization of unstructured language is Named Entity Recognition (NER), which is language specific. We are the experts for the South Slavic language group.