Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
We describe a simple and effective method (Spectral Attribute removaL; SAL) to remove private or guarded information from neural representations. Our method uses matrix decomposition to project the input representations into directions with reduced covariance with the guarded information rather than...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We describe a simple and effective method (Spectral Attribute removaL; SAL)
to remove private or guarded information from neural representations. Our
method uses matrix decomposition to project the input representations into
directions with reduced covariance with the guarded information rather than
maximal covariance as factorization methods normally use. We begin with linear
information removal and proceed to generalize our algorithm to the case of
nonlinear information removal using kernels. Our experiments demonstrate that
our algorithm retains better main task performance after removing the guarded
information compared to previous work. In addition, our experiments demonstrate
that we need a relatively small amount of guarded attribute data to remove
information about these attributes, which lowers the exposure to sensitive data
and is more suitable for low-resource scenarios. Code is available at
https://github.com/jasonshaoshun/SAL. |
---|---|
DOI: | 10.48550/arxiv.2203.07893 |