Hybrid neural network is protected against adversarial attacks using various defense techniques, including input transformation, randomization, and adversarial training.

A quantum-classical (or hybrid) neural network and the use of a adversarial attack mechanism. The core libraries employed are Quantinuum pytket and pytket-qiskit. torchattacks is used for the white-box, targetted, compounded adversarial attacks.

A tutorial on classical to quantum transfer learning by Xanadu AI

Hybrid neural network model is protected against adversarial attacks using either adversarial training or randomization defense techniques

Quantum Finance Library

A comparison analysis between classical and quantum-classical (or hybrid) neural network and the impact effectiveness of a compound adversarial attack.

DDQCL implementation using Qiskit. Variational quantum circuit that maps a randomly generated set of four 4-qubit input states to four 4-qubit output states. Circuit parameters are refined over time to get the lowest cost parameter set.

The official code repository for "Variational Quanvolutional Neural Networks with enhanced image encoding", https://arxiv.org/abs/2106.07327

A dynamically executed quantum-classical hybrid runtime.

Fast and flexible nonadiabatic molecular dynamics in Julia!

GW-BSE for excited state Quantum Chemistry in a Gaussian Orbital basis, electronic spectroscopy with QM/MM, charge and energy dynamics in complex molecular systems