Glossary
What is a quasi-identifier?
A quasi-identifier, or indirect identifier, is a detail that does not name a person on its own but can identify them in combination with other details or outside knowledge. Ontario's privacy commissioner lists examples including date of birth or age, event dates, postal codes, building names, regions and profession. The classic case: ZIP code, birth date and sex together made most Americans unique in 1990 census data.
Last reviewed · 3 sources
The definition in the guidance
Ontario's IPC De-identification Guidelines describe quasi-identifiers as variables that "an adversary is assumed to have background knowledge of" and that "can be used, either individually or in combination" to identify people. Its examples include "gender, date of birth or age, event dates", "locations (e.g., postal codes, building names, regions)", "country of birth", "profession" and "marital status".
The UK ICO lists "sex, age, occupation, place of residence, country of birth" as key variables to mask or tokenise.
Why they matter
NIST's NISTIR 8053 recounts the finding that "up to 87% of the U.S. population could be uniquely identified by their 5-digit ZIP code, date of birth, and sex" in the 1990 census. None of the three is a name; together they work like one.
In a client document, the quasi-identifiers are often the facts the task needs: an age, an occupation, an income. The skill is keeping the ones that matter and reducing the rest.
Where PiBye fits
How PiBye handles this
PiBye replaces the address-scale quasi-identifiers, such as full postal and ZIP codes and dates of birth, automatically, and shows you the whole approved copy so you can judge the rest, like a rare job title, before anything is shared.
1.0.1 · macOS 14.8.5 or later · Apple Silicon · 1.1 GB
Frequently asked questions
Is occupation a quasi-identifier?
Yes. Ontario's IPC and the UK ICO both list it. A common job adds little risk; a singular role can identify someone by itself.
Should every quasi-identifier be removed?
No. Remove or generalize the ones the task does not need. Removing everything leaves a document the AI cannot reason about.
Sources
- De-identification Guidelines for Structured Data, Information and Privacy Commissioner of Ontario, June 2016. Checked 25 September 2026.
- How do we ensure anonymisation is effective?, Information Commissioner's Office (UK). Checked 25 September 2026.
- NISTIR 8053: De-Identification of Personal Information, National Institute of Standards and Technology, October 2015. Checked 25 September 2026.