journalarticle
When Does Data Augmentation Help With Membership Inference Attacks?
International Conference on Machine Learning2021 90 citations30 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
No abstract is available from our sources. Use “Read paper” to view it.
TL;DRIt is found that applying augmentation to increase the model’s utility does not mitigate the risk and protection comes with a utility penalty, and practical guidelines on using augmentation to manage the trade-off are provided. (Semantic Scholar)