Paper 2018/206

Reading in the Dark: Classifying Encrypted Digits with Functional Encryption

Edouard Dufour-Sans, Romain Gay, and David Pointcheval


As machine learning grows into a ubiquitous technology that finds many interesting applications, the privacy of data is becoming a major concern. This paper deals with machine learning and encrypted data. Namely, our contribution is twofold: we first build a new Functional Encryption scheme for quadratic multi-variate polynomials, which outperforms previous schemes. It enables the efficient computation of quadratic polynomials on encrypted vectors, so that only the result is in clear. We then turn to quadratic networks, a class of machine learning models, and show that their design makes them particularly suited to our encryption scheme. This synergy yields a technique for efficiently recovering a plaintext classification of encrypted data. Eventually, we prototype our construction and run it on the MNIST dataset to demonstrate practical relevance. We obtain 97.54% accuracy, with decryption and encryption taking few seconds.

Available format(s)
Publication info
Preprint. MINOR revision.
Machine Learning on Encrypted DataFunctional EncryptionQuadratic polynomials
Contact author(s)
edufoursans @ ens fr
2020-10-26: last of 2 revisions
2018-02-22: received
See all versions
Short URL
Creative Commons Attribution


      author = {Edouard Dufour-Sans and Romain Gay and David Pointcheval},
      title = {Reading in the Dark: Classifying Encrypted Digits with Functional Encryption},
      howpublished = {Cryptology ePrint Archive, Paper 2018/206},
      year = {2018},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.