Adversarial Attacks Defense for Continuous Variable Quantum Key Distribution System Based on Diffusion Model

Deep learning is applied to continuous-variable quantum key distribution (CVQKD) systems for attack detection and classification. However, adversarial attacks can bypass these detection mechanisms, posing a significant threat. To address this, we introduce QuantumPure, a defense mechanism based on a diffusion model that purifies adversarial inputs. QuantumPure first introduces controlled noise to the adversarial data through a forward diffusion process, then applies a reverse sampling step to reconstruct clean data. This approach ensures that adversarial perturbations are neutralized while preserving the integrity of the quantum data. We demonstrate that QuantumPure enhances the robustness of CVQKD systems across a broad spectrum of adversarial attacks, encompassing both white-box and black-box scenarios while preserving high classification accuracy. Furthermore, the results demonstrate that our approach is resistant to unseen attack methods and greatly enhances the security of communication systems.