Quantum Privacy-Preserving Perceptron
This addresses privacy concerns for users of machine learning systems by protecting sensitive training data, though it appears incremental as it builds on existing privacy-preserving methods with quantum enhancements.
The paper tackles privacy risks in machine learning training by proposing a quantum privacy-preserving algorithm for perceptrons, which uses quantum tests to detect dishonesty and private random noise to protect data, claiming better protection than classical methods without requiring a quantum database.
With the extensive applications of machine learning, the issue of private or sensitive data in the training examples becomes more and more serious: during the training process, personal information or habits may be disclosed to unexpected persons or organisations, which can cause serious privacy problems or even financial loss. In this paper, we present a quantum privacy-preserving algorithm for machine learning with perceptron. There are mainly two steps to protect original training examples. Firstly when checking the current classifier, quantum tests are employed to detect data user's possible dishonesty. Secondly when updating the current classifier, private random noise is used to protect the original data. The advantages of our algorithm are: (1) it protects training examples better than the known classical methods; (2) it requires no quantum database and thus is easy to implement.