You are here

De-identify data

zeros and ones banner image

De-identification enables sharing of data for secondary purposes. Changes may be made to the data and controls can be put in place to manage risk.

This workshop will introduce a risk-based methodology for de-identification that is appropriate for various academic disciplines. Topics include: in/direct identifiers, risk thresholds and measurement, plausible attacks, techniques (generalization, suppression, and subsampling), documentation, equivalence classes, and k-anonymity.

The workshop uses content from an eBook available through SFU Library:

Emam, K. E., & Arbuckle, L. (2013). Anonymizing Health Data: Case Studies and Methods to Get You Started. Sebastopol, CA, USA: O’Reilly Media, Inc. Retrieved from


Upcoming Workshops

No upcoming instances of this workshop found.