Litcius/Paper detail

MP2ML

Fabian Boemer, Rosario Cammarota, Daniel Demmler, Thomas Schneider, Hossein Yalame

202058 citationsDOI

Abstract

Privacy-preserving machine learning (PPML) has many applications, from medical image classification and anomaly detection to financial analysis. nGraph-HE enables data scientists to perform private inference of deep learning (DL) models trained using popular frameworks such as TensorFlow. nGraph-HE computes linear layers using the CKKS homomorphic encryption (HE) scheme. The non-polynomial activation functions, such as MaxPool and ReLU, are evaluated in the clear by the data owner who obtains the intermediate feature maps. This leaks the feature maps to the data owner from which it may be possible to deduce the DL model weights. As a result, such protocols may not be suitable for deployment, especially when the DL model is intellectual property.

Topics & Concepts

Homomorphic encryptionComputer scienceFeature (linguistics)Software deploymentInferencePolynomialScheme (mathematics)Deep learningArtificial intelligenceEncryptionImage (mathematics)Data miningComputer securityMathematicsMathematical analysisPhilosophyOperating systemLinguisticsCryptography and Data SecurityPrivacy-Preserving Technologies in DataComplexity and Algorithms in Graphs