Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning

Abstract

Quantum machine learning (QML) is emerging as an application of quantum computing with the potential to deliver quantum advantage, but its realisation for practical applications remains impeded by challenges. Amongst those, a key barrier is the computationally expensive task of encoding classical data into a quantum state, which could erase any prospective speed-ups over classical algorithms. In this work, we implement methods for the efficient preparation of quantum states representing encoded image data using variational, genetic and matrix product state based algorithms. Our results show that these methods can approximately prepare states to a level suitable for QML using circuits two orders of magnitude shallower than a standard state preparation implementation, obtaining drastic savings in circuit depth and gate count without unduly sacrificing classification accuracy. Additionally, the QML models trained and evaluated on approximately encoded data display an increased robustness to adversarially generated input data perturbations. This partial alleviation of adversarial vulnerability, possible due to the "drowning out" of adversarial perturbations while retaining the meaningful large-scale features of the data, constitutes a considerable benefit for approximate state preparation in addition to lessening the requirements of the quantum hardware. Our results, based on simulations and experiments on IBM quantum devices, highlight a promising pathway for the future implementation of accurate and robust QML models on complex datasets relevant for practical applications, bringing the possibility of NISQ-era QML advantage closer to reality.

arXiv comment14 pages, 8 figures

References in corpus (48)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Quantum Machine Learning
• The density-matrix renormalization group in the age of matrix product states
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Efficient classical simulation of slightly entangled quantum computations
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• Quantum Convolutional Neural Networks
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
• Evaluating Large Language Models Trained on Code
• Robust Speech Recognition via Large-Scale Weak Supervision
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evasion Attacks against Machine Learning at Test Time
• Efficient Learning for Deep Quantum Neural Networks
• Efficient quantum state tomography
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Adversarial Examples Are Not Bugs, They Are Features
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Sequential generation of entangled multi-qubit states
• Imagen Video: High Definition Video Generation with Diffusion Models
• Robust data encodings for quantum classifiers
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Quantum Circuits for Isometries
• Certified Adversarial Robustness with Additive Noise
• Quantum noise protects quantum classifiers against adversaries
• Encoding of Matrix Product States into Quantum Circuits of One- and Two-Qubit Gates
• Quantum Adversarial Machine Learning
• Demonstration of non-Markovian process characterisation and control on a quantum processor
• Experimental quantum adversarial learning with programmable superconducting qubits
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Vulnerability of quantum classification to adversarial perturbations
• Towards quantum enhanced adversarial robustness in machine learning
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Decomposition of Unitary Matrices for Finding Quantum Circuits: Application to Molecular Hamiltonians
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing
• Robustness Verification of Quantum Classifiers
• Provably Trainable Rotationally Equivariant Quantum Machine Learning
• Boosted Ensembles of Qubit and Continuous Variable Quantum Support Vector Machines for B Meson Flavour Tagging
• Exploring the optimality of approximate state preparation quantum circuits with a genetic algorithm
• Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines

Cited by in corpus (10)

• Efficient MPS representations and quantum circuits from the Fourier modes of classical image data
• Non-Unitary Quantum Machine Learning
• Designing Robust Quantum Neural Networks via Optimized Circuit Metrics
• Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers
• Self-Adaptive Quantum Kernel Principal Components Analysis for Compact Readout of Chemiresistive Sensor Arrays
• Adversarial Robustness Guarantees for Quantum Classifiers
• Almost fault-tolerant quantum machine learning with drastic overhead reduction
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Quantum Encoding of Structured Data with Matrix Product States
• Classical Autoencoder Distillation of Quantum Adversarial Manipulations