Towards quantum enhanced adversarial robustness in machine learning

Abstract

Machine learning algorithms are powerful tools for data driven tasks such as image classification and feature detection, however their vulnerability to adversarial examples - input samples manipulated to fool the algorithm - remains a serious challenge. The integration of machine learning with quantum computing has the potential to yield tools offering not only better accuracy and computational efficiency, but also superior robustness against adversarial attacks. Indeed, recent work has employed quantum mechanical phenomena to defend against adversarial attacks, spurring the rapid development of the field of quantum adversarial machine learning (QAML) and potentially yielding a new source of quantum advantage. Despite promising early results, there remain challenges towards building robust real-world QAML tools. In this review we discuss recent progress in QAML and identify key challenges. We also suggest future research directions which could determine the route to practicality for QAML approaches as quantum computing hardware scales up and noise levels are reduced.

arXiv comment10 Pages, 4 Figures

References in corpus (51)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Quantum Machine Learning
• Generative Adversarial Networks
• Generative Adversarial Networks: An Overview
• Surface codes: Towards practical large-scale quantum computation
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• One pixel attack for fooling deep neural networks
• Suppressing quantum errors by scaling a surface code logical qubit
• Theoretically Principled Trade-off between Robustness and Accuracy
• Evasion Attacks against Machine Learning at Test Time
• Efficient Learning for Deep Quantum Neural Networks
• Quantum generative adversarial learning
• Certified Defenses against Adversarial Examples
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Quantum generative adversarial networks
• Quantum autoencoders for efficient compression of quantum data
• Fast is better than free: Revisiting adversarial training
• Generalization in quantum machine learning from few training data
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Adversarial Examples Are Not Bugs, They Are Features
• Robust data encodings for quantum classifiers
• Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
• Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
• Demonstration of quantum advantage in machine learning
• Supervised quantum machine learning models are kernel methods
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Quantum noise protects quantum classifiers against adversaries
• Quantum Adversarial Machine Learning
• Demonstration of non-Markovian process characterisation and control on a quantum processor
• Scaling provable adversarial defenses
• Experimental quantum adversarial learning with programmable superconducting qubits
• An Abstraction-Based Framework for Neural Network Verification
• A unified framework for magic state distillation and multi-qubit gate-synthesis with reduced resource cost
• Vulnerability of quantum classification to adversarial perturbations
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Experimental exploration of five-qubit quantum error correcting code with superconducting qubits
• Quantum Neural Network Classifiers: A Tutorial
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing
• Robustness Verification of Quantum Classifiers
• An efficient magic state approach to small angle rotations
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Transfer of Adversarial Robustness Between Perturbation Types
• Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines
• Adversarial Machine Learning Phases of Matter
• Cost-optimal single-qubit gate synthesis in the Clifford hierarchy

Cited by in corpus (19)

• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• QFaaS: A Serverless Function-as-a-Service Framework for Quantum Computing
• Provably Trainable Rotationally Equivariant Quantum Machine Learning
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Calibrating the role of entanglement in variational quantum circuits
• Training robust and generalizable quantum models
• Boosted Ensembles of Qubit and Continuous Variable Quantum Support Vector Machines for B Meson Flavour Tagging
• Designing Robust Quantum Neural Networks via Optimized Circuit Metrics
• Adversarial Robustness Guarantees for Quantum Classifiers
• Quantum Kernel Learning for Small Dataset Modeling in Semiconductor Fabrication: Application to Ohmic Contact
• Self-Adaptive Quantum Kernel Principal Components Analysis for Compact Readout of Chemiresistive Sensor Arrays
• Quantum computer error structure probed by quantum error correction syndrome measurements
• Quantum Next-Generation Reservoir Computing and Its Quantum Optical Implementation
• Coherence Fraction in Grover Search Algorithm
• Almost fault-tolerant quantum machine learning with drastic overhead reduction
• Decoding Quantum Search Advantage: The Critical Role of State Properties in Random Walks
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Detecting underdetermination in parameterized quantum circuits