QFAL: Quantum Federated Adversarial Learning
This addresses adversarial vulnerabilities in quantum federated learning, which is an incremental advancement combining adversarial training with QFL to enhance robustness in privacy-preserving quantum systems.
This work tackles the vulnerability of quantum federated learning (QFL) to adversarial attacks by integrating adversarial training into QFL, proposing a robust framework called quantum federated adversarial learning (QFAL). The results show that while fewer clients yield higher clean-data accuracy, larger federations can better balance accuracy and robustness with partial adversarial training, and even limited adversarial coverage (e.g., 20%-50%) significantly improves resilience to moderate perturbations at the cost of reduced baseline performance.
Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNNs), yet its vulnerability to adversarial attacks remains poorly understood. This work pioneers the integration of adversarial training into QFL, proposing a robust framework, quantum federated adversarial learning (QFAL), where clients collaboratively defend against perturbations by combining local adversarial example generation with federated averaging (FedAvg). We systematically evaluate the interplay between three critical factors: client count (5, 10, 15), adversarial training coverage (0-100%), and adversarial attack perturbation strength (epsilon = 0.01-0.5), using the MNIST dataset. Our experimental results show that while fewer clients often yield higher clean-data accuracy, larger federations can more effectively balance accuracy and robustness when partially adversarially trained. Notably, even limited adversarial coverage (e.g., 20%-50%) can significantly improve resilience to moderate perturbations, though at the cost of reduced baseline performance. Conversely, full adversarial training (100%) may regain high clean accuracy but is vulnerable under stronger attacks. These findings underscore an inherent trade-off between robust and standard objectives, which is further complicated by quantum-specific factors. We conclude that a carefully chosen combination of client count and adversarial coverage is critical for mitigating adversarial vulnerabilities in QFL. Moreover, we highlight opportunities for future research, including adaptive adversarial training schedules, more diverse quantum encoding schemes, and personalized defense strategies to further enhance the robustness-accuracy trade-off in real-world quantum federated environments.