Preventing Adversarial Use of Datasets through Fair Core-Set Construction
2019
We propose improving the privacy properties of a dataset by publishing only a strategically chosen "core-set" of the data containing a subset of the instances. The core-set allows strong performance on primary tasks, but forces poor performance on unwanted tasks. We give methods for both linear models and neural networks and demonstrate their efficacy on data.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
8
References
0
Citations
NaN
KQI