Differentiable architecture search for adversarially robust quantum computer vision

2026-01-20

Quantum Machine Intelligence

AI Summary

This work addresses the vulnerability of quantum neural networks to adversarial perturbations and hardware noise, which hinders their practical deployment. The authors propose a hybrid quantum-classical differentiable architecture search framework that integrates a lightweight classical noise layer before the quantum circuit and jointly optimizes the circuit topology, gate selection, and noise parameters via gradient-based methods. This approach represents the first integration of differentiable quantum architecture search (DQAS) with a classical preprocessing noise layer, significantly enhancing model robustness without compromising accuracy on clean data. Experimental results demonstrate that the framework achieves strong resilience against diverse adversarial attacks—including FGSM, PGD, BIM, and MIM—as well as realistic quantum noise across MNIST, FashionMNIST, and CIFAR datasets, with validation on actual quantum hardware confirming its effectiveness.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Adversarial Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Current quantum neural networks suffer from extreme sensitivity to both adversarial perturbations and hardware noise, creating a significant barrier to real-world deployment. Existing robustness techniques typically sacrifice clean accuracy or require prohibitive computational resources. We propose a hybrid quantum-classical Differentiable Quantum Architecture Search (DQAS) framework that addresses these limitations by jointly optimizing circuit structure and robustness through gradient-based methods. Our approach enhances traditional DQAS with a lightweight Classical Noise Layer applied before quantum processing, enabling simultaneous optimization of gate selection and noise parameters. This design preserves the quantum circuit’s integrity while introducing trainable perturbations that enhance robustness without compromising standard performance. Experimental validation on MNIST, FashionMNIST, and CIFAR datasets shows consistent improvements in both clean and adversarial accuracy compared to existing quantum architecture search methods. Under various attack scenarios, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM), and under realistic quantum noise conditions, our hybrid framework maintains superior performance. Testing on actual quantum hardware confirms the practical viability of discovered architectures. These results demonstrate that strategic classical preprocessing combined with differentiable quantum architecture optimization can significantly enhance quantum neural network robustness while maintaining computational efficiency.

Problem

• quantum neural networks
• adversarial robustness
• hardware noise
• differentiable architecture search
• quantum computer vision

Innovation

• Differentiable Quantum Architecture Search
• Adversarial Robustness
• Classical Noise Layer
• Hybrid Quantum-Classical Framework
• Quantum Neural Networks