EPIC: efficient private image classification (or: learning from the masters)

DOI10.1007/978-3-030-12612-4_24MaRDI QIDQ2290468zbMATH OpenOpenAlexFDO

Authors Eleftheria Makri, Dragos Rotaru, N. P. Smart, Frederik Vercauteren

Publication date 28 January 2020

Full work available at URL https://lirias.kuleuven.be/handle/123456789/637523

Mathematics Subject Classification ID

Privacy of data (68P27) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Privacy-preserving classifier learning
• Protect privacy of deep classification networks by exploiting their generative power
• EPiC: efficient privacy-preserving counting for MapReduce
• Nearly optimal private convolution
• Preserving differential privacy in convolutional deep belief networks

Cited in

(6)

• SPEED: secure, private, and efficient deep learning
• MArBLed circuits: mixing arithmetic and Boolean circuits with active security
• EPiC: efficient privacy-preserving counting for MapReduce
• PPOIM: privacy-preserving shape context based image denoising and matching with efficient outsourcing
• Maliciously secure matrix multiplication with applications to private deep learning
• \textsf{Through the looking-glass}: benchmarking secure multi-party computation comparisons for \textsf{ReLU}'s

This page was built for publication: EPIC: efficient private image classification (or: learning from the masters)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2290468)