IFIP Summer School on Privacy and Identity Management, 18-23 August 2019, Brugg Windisch, Switzerland
With the advent of the big data technologies which bring better scalability and performance results, machine learning (ML) algorithms become affordable in a number of different applications and areas. The use of large volumes of data to obtain accurate predictions unfortunately come with a high cost in terms of privacy exposures. The
underlying data are often personal or condential and therefore need to be properly safeguarded. Given the cost of machine learning algorithms, these would need to be outsourced to third-party servers and hence the encryption of the data becomes mandatory. While traditional data encryption solutions would not allow for the access over the content of the data, these would, nevertheless, prevent third-party servers to properly execute the ML algorithms. The goal is therefore to come up with customized ML algorithms that would by design preserve the privacy of the processed data. Advanced cryptographic techniques such as fully homomorphic encryption or secure multi-party computation enable the execution of some operations over encrypted data and therefore can be considered as potential candidates for these algorithms. Yet, these incur high computational and/or communication costs for some operations. In this
paper, we propose a Systematization of Knowledge (SoK) whereby we analyze the tension between a particular ML technique, namely, neural networks (NN), and the characteristics of relevant cryptographic tools.
© IFIP. Personal use of this material is permitted. The definitive version of this paper was published in IFIP Summer School on Privacy and Identity Management, 18-23 August 2019, Brugg Windisch, Switzerland and is available at : http://dx.doi.org/10.1007/978-3-030-42504-3_5