Fig. 1: Overview of the general framework and definitions. | npj Quantum Information

Fig. 1: Overview of the general framework and definitions.

From: Characterizing privacy in quantum machine learning

Fig. 1

Weak privacy breach corresponds to attacks where snapshots of the data are retrieved. These can be used as inputs to other models, without explicitly needing the exact data, allowing one to potentially learn characteristics of the data. If these snapshots can then be further inverted to retrieve the input data x explicitly, we say the attack has succeeded in a strong privacy breach.

Back to article page