AB  - © 2017 IEEE. More and more quantum algorithms have been designed for solving problems in machine learning, database search and data analytics. An important problem then arises: how privacy can be protected when these algorithms are used on private data? For classical computing, the notion of differential privacy provides a very useful conceptual framework in which a great number of mechanisms that protect privacy by introducing certain noises into algorithms have been successfully developed. This paper defines a notion of differential privacy for quantum information processing. We carefully examine how the mechanisms using three important types of quantum noise, the amplitude/phase damping and depolarizing, can protect differential privacy. A composition theorem is proved that enables us to combine multiple privacy-preserving operations in quantum information processing.
AU  - Zhou, L
AU  - Ying, M
DA  - 2017/09/25
DO  - 10.1109/CSF.2017.23
EP  - 262
JO  - Proceedings - IEEE Computer Security Foundations Symposium
PY  - 2017/09/25
SP  - 249
TI  - Differential Privacy in Quantum Computation
Y1  - 2017/09/25
Y2  - 2026/05/28
ER  -