Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning.
Karthik GarimellaNandan Kumar JhaBrandon ReagenPublished in: CoRR (2021)
Keyphrases
- low degree
- privacy preserving
- deep learning
- privacy preserving data mining
- unsupervised learning
- vertically partitioned data
- privacy preservation
- uniform distribution
- mental models
- machine learning
- privacy concerns
- weakly supervised
- agnostic learning
- sensitive information
- data privacy
- private information
- decision lists
- text classification
- secure multiparty computation
- data mining
- differential privacy
- multi class