Quantum neural networks use noise for robust intrusion detection · arXiv research

This paper introduces a rigorous theoretical framework for stochastic quantum neural networks (SQNNs) to enhance adversarial robustness in network intrusion detection. The research proposes a "decoherence-contraction theorem" that quantifies how noise, specifically a depolarizing channel, can contract adversarial perturbations. Experiments on the NSL-KDD dataset demonstrate that SQNNs trained with this noise are significantly more robust against attacks like FGSM and PGD compared to noiseless models, avoiding catastrophic robustness collapse. The study also derives an adaptive-penalty formula for noise regularization, comparing per-gate dropout with depolarizing noise and finding them statistically indistinguishable in reducing the train-test gap. AI

IMPACT Introduces a novel approach to enhance adversarial robustness in AI systems using quantum principles, potentially leading to more secure AI applications.

RANK_REASON The cluster contains a research paper published on arXiv detailing theoretical and experimental findings in quantum neural networks.

Read on arXiv cs.CL →

• arXiv
• Decoherence as Defence and the Magnitude of Noise Regularisation: A Rigorous N -Qubit Theory of Stochastic Quantum Neural Networks for Adversarially Robust Network Intrusion Detection
• Du et al.
• FGSM
• Lindblad master equation approach to superconductivity in open quantum systems
• NSL KDD
• Pauli
• Projected Gradient Descent
• Stochastic Quantum Neural Networks

• paper
• safety
• infra

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →