The Robustness Verification of Linear Sound Quantum Classifiers
This addresses robustness verification for quantum machine learning practitioners, but it is incremental as it builds on existing Linear Sound Property concepts.
The authors tackled the problem of verifying robustness in quantum classifiers by introducing a quick and sound method for Linear Sound classifiers, successfully applying it to a Quantum Convolutional Neural Network on the MNIST dataset.
I present a quick and sound method for the robustness verification of a sort of quantum classifiers who are Linear Sound. Since quantum machine learning has been put into practice in relevant fields and Linear Sound Property, LSP is a pervasive property, the method could be universally applied. I implemented my method with a Quantum Convolutional Neural Network, QCNN using MindQuantum, Huawei and successfully verified its robustness when classifying MNIST dataset.