Privacy-preserving quantum machine learning using differential privacy
Makhamisa Senekane, Mhlambululi Mafu, Benedict Molibeli Taele · 2017
The advance of artificial intelligence in general and machine learning in particular has resulted in the need to pay more attention to the provision of privacy to the data being anlyzed. An example of sensitive data analysis might be in the analysis of individuals' medical records. In such a case, there might be a need to draw insights from data while at the same time maintaining privacy of the participants. Such cases have given birth to privacy-preserving data analyitics. Privacy is typically guaranteed by a differentially private mechanism. In this paper, we present a novel mechanism for privacy-preserving quantum machine learning. The mechanism is tested on the sensitive dataset that contains features and target labels for breast cancer prediction. The results obtained underline the utility of this mechanism.