Outcome Indistinguishability
Name
3406325.3451064.pdf
Size
718.29 KB
Format
Adobe PDF
Checksum (MD5)
2bc7631868df34c847005a69df4a97d8
Author(s)
Dwork, Cynthia
Kim, Michael P.
Reingold, Omer
Rothblum, Guy N.
Yona, Gal
Date Issued
June 15, 2021
Publisher
Association for Computing Machinery
Citation
Cynthia Dwork, Michael P. Kim, Omer Reingold, Guy N. Rothblum, and Gal Yona. 2021. Outcome indistinguishability. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing (STOC 2021). Association for Computing Machinery, New York, NY, USA, 1095–1108.
Version
Final published version
Abstract
Prediction algorithms assign numbers to individuals that are popularly understood as individual “probabilities”—what is the probability of 5-year survival after cancer diagnosis?—and which increasingly form the basis for life-altering decisions. Drawing on an understanding of computational indistinguishability developed in complexity theory and cryptography, we introduce Outcome Indistinguishability. Predictors that are Outcome Indistinguishable (OI) yield a generative model for outcomes that cannot be efficiently refuted on the basis of the real-life observations produced by. We investigate a hierarchy of OI definitions, whose stringency increases with the degree to which distinguishers may access the predictor in question. Our findings reveal that OI behaves qualitatively differently than previously studied notions of indistinguishability. First, we provide constructions at all levels of the hierarchy. Then, leveraging recently-developed machinery for proving average-case fine-grained hardness, we obtain lower bounds on the complexity of the more stringent forms of OI. This hardness result provides the first scientific grounds for the political argument that, when inspecting algorithmic risk prediction instruments, auditors should be granted oracle access to the algorithm, not simply historical predictions.
Description
STOC ’21, June 21–25, 2021, Virtual, Italy
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3406325.3451064
