Membership Encoding for Deep Learning

Explore this paper's citation graph

Summary

This paper presents membership encoding for training deep neural networks and encoding the membership information, i.e. whether a data point is used for training, for a subset of training data, and the encoding algorithm can determine the membership of significantly redacted data points.

Type
preprint
Published
2019-09-27
Cited by
6
References
45
Access
Open access

Keywords

Encoding (memory), Computer science, Embedding, Digital watermarking, Deep learning

References

Cited by

Related papers