Simulated algorithm audits show that synthetic data and small or incomplete audit samples can make group-parity metrics unreliable, while differentially private aggregate statistics generally remain reliable.
Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.HC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Access Denied: Meaningful Data Access for Quantitative Algorithm Audits
Simulated algorithm audits show that synthetic data and small or incomplete audit samples can make group-parity metrics unreliable, while differentially private aggregate statistics generally remain reliable.