Skip to content
Roy Saurabh

BA-FedSHAP: A reproducible toolkit for auditing background-induced attribution drift

Venue
SSRN
Year
2026
Role
Author
Generated pattern.

Abstract

Preprint on how the choice of background distribution alters federated attribution results, and what that does to an audit.

Role

Author

Authors. Roy Saurabh

Evidence

  1. 01

    SSRN (Elsevier)

    BA-FedSHAP preprint

    Registers the BA-FedSHAP preprint, authored by Roy Saurabh, as posted content on SSRN.

    View original ↗, opens in a new tabDOI ↗, opens in a new tab

Citation

Roy, S. (2026). BA-FedSHAP: A reproducible toolkit for auditing background-induced attribution drift [Preprint]. SSRN. https://doi.org/10.2139/ssrn.6864992

Related

AI in health

AI in health: how smart technology is breaking new frontiers in medical care