Preserving Personal Data Privacy in the Age of AI: A Practical Approach with Nerpii
summary
Nerpii is an open-source Python library that detects personal data in structured datasets using Named Entity Recognition and replaces it with synthetic values so you can train ML models without exposing real PII. The talk covers privacy risks of using sensitive data in AI/ML (especially in healthcare, insurance, banking) and demonstrates generating synthetic data with generative AI to preserve statistical properties while protecting individual privacy.
AI-written summary · about
chapters (7)
- 0:00Privacy and synthetic data
- 2:40Generate synthetic data
- 7:21Direct vs indirect identifiers
- 10:11Nerpii library
- 13:41How Nerpii works
- 16:37Limitations and future
- 18:00Q&A
related talks
54mOpen Data vs. Privacy - How Synthetic Data Can Democratize AI Innovation
40mBalancing Privacy & Utility: Efficient PII Detection and Replacement in Textual Data
20mSynthetic Data for Privacy, AI Fairness and Democratizing Data Access
33mMachine Learning in the age of increasing Data Privacy Consciousness
25mPrivacy Nightmares while Using ML/AI
29mPersonal Data Pseudonymization Versus Anonymization In The Age Of AI & Big Data
28mInsights, Not Secrets: How Synthetic Data Empowers Privacy
17mDon't Stop at Data Democratization!