liveBook · Manning

Privacy-enhancing technology

As explained in Introduction to Generative AI, Second Edition

A privacy-enhancing technology is a technical method that reduces the collection, exposure, linkability, or identifiability of personal information.

A generative AI model can repeat sensitive information from its training data. Privacy-enhancing technologies (PETs) are methods that reduce privacy risks, including the risk that information can be traced back to a person. They include anonymization, pseudonymization, data masking, and differential privacy. section 3.4 section 3.17

Sensitive data in email

Research involving the Enron Email Dataset found that credit card and Social Security numbers could be extracted with minimal effort. The finding illustrates why unintended memorization is a privacy concern. section 3.4

One approach is to filter training data using blocklists of potentially sensitive sequences. Blocklists can remove known patterns, but they cannot protect against memorization of unseen or rare content. More generally, sensitive information can be hard to find in large datasets, and masking it can disrupt the language patterns a model learns from. section 3.4 section 10.18

Differential privacy introduces statistical noise during training to limit the influence of any individual data point. It can be difficult to implement for large language models without sacrificing usefulness, and it does not prevent memorization of unique, infrequent strings. section 3.4

PETs reduce risk rather than eliminate it. Even after direct identifiers are removed, personal information may be inferred from apparently harmless data. Technical protections therefore sit alongside measures such as privacy risk assessments, internal review, and clear data policies. section 3.17 section 10.18

How Introduction to Generative AI, Second Edition covers it

How deep it goes
Defines PETs and compares their limitations and trade-offs without implementation details.
Examples
Uses sensitive-number extraction from the Enron Email Dataset and training-data blocklists to illustrate privacy risks and mitigation.
What you can do after
Evaluate and understand privacy protections for generative AI while recognizing their limitations and trade-offs.
How it connects
Connects PETs to unintended memorization, differential privacy, data masking, and privacy risk assessment.

Also explained in

Compare how 2 books explain privacy-enhancing technology →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Introduction to Generative AI, Second Edition. The section links point to the parts of the book it draws on.