Microsoft Presidio 2.2.33: batch anonymization and GPT-3 synthetic data
In one sentence Release 2.2.33 of Presidio, Microsoft's open source framework for detecting and anonymizing personal data in text, adds batch anonymization, the keep operator, a Streamlit demo and a GPT-3 based synthetic data generation example.
When a company uses an LLM to analyze emails, contracts or support tickets, it risks sending customers' personal data to external services. This is a serious problem for GDPR and privacy regulations.
Presidio is Microsoft's open source framework built for this: it analyzes text, finds personal information (names, phone numbers, IBANs, ID documents) and replaces, masks or encrypts it before the text is used elsewhere.
Version 2.2.33, from June 2023, adds batch anonymization of lists and dicts, an operator that leaves detected entities untouched, a new Streamlit-based demo app and a GPT-3 synthetic data generation example. It drops Python 3.7 and adds Python 3.11. Presidio is not new: the changelog of the 2.x series goes back to 2021.
Companies
Microsoft
Tools
Presidio, spaCy
Tags
Sources