Overlearning Reveals Sensitive Attributes

ICLR, 2020.

Cited by: 0|Bibtex|Views20
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org

Abstract:

``"Overlearningu0027u0027 means that a model trained for a seemingly simple objective implicitly learns to recognize attributes and concepts that are (1) not part of the learning objective, and (2) sensitive from a privacy or bias perspective. For example, a binary gender classifier of facial images also learns to recognize races, even ra...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments