✳flâneur — a map of the web's best reading

Why not differential privacy? - Ted is writing things

desfontain.es · 2,027 words · saved by 1 readers

What does it mean for an algorithm to not be differentially private?

T his post is part of a series on differential privacy . Check out the table of contents to see the other articles! S ome algorithms are not differentially private, but still claim to perform anonymization. Such mechanisms are common, both in the academic literature and in industry. Explanations on why they still preserve some notion of privacy vary. They might include some ad hoc protections against entire classes of attacks. They might aggregate the data to a point where the statistics "obviously" seem safe. They might use some other metric for data leakage, like entropy or mutual informatio

Explore this link on the map →

saved by

related reading