The paper presents a differentially private methodology and a public synthetic dataset of Topics API traces that match real re-identification risk within one standard deviation on two attacks.
A Quantitative Information Flow Analysis of the Topics API
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Differentially Private Synthetic Data Release for Topics API Outputs
The paper presents a differentially private methodology and a public synthetic dataset of Topics API traces that match real re-identification risk within one standard deviation on two attacks.