Quantum noise protects quantum classifiers against adversaries

Abstract

Noise in quantum information processing is often viewed as a disruptive and difficult-to-avoid feature, especially in near-term quantum technologies. However, noise has often played beneficial roles, from enhancing weak signals in stochastic resonance to protecting the privacy of data in differential privacy. It is then natural to ask, can we harness the power of quantum noise that is beneficial to quantum computing? An important current direction for quantum computing is its application to machine learning, such as classification problems. One outstanding problem in machine learning for classification is its sensitivity to adversarial examples. These are small, undetectable perturbations from the original data where the perturbed data is completely misclassified in otherwise extremely accurate classifiers. They can also be considered as `worst-case' perturbations by unknown noise sources. We show that by taking advantage of depolarisation noise in quantum circuits for classification, a robustness bound against adversaries can be derived where the robustness improves with increasing noise. This robustness property is intimately connected with an important security concept called differential privacy which can be extended to quantum differential privacy. For the protection of quantum data, this is the first quantum protocol that can be used against the most general adversaries. Furthermore, we show how the robustness in the classical case can be sensitive to the details of the classification model, but in the quantum case the details of classification model are absent, thus also providing a potential quantum advantage for classical data that is independent of quantum speedups. This opens the opportunity to explore other ways in which quantum noise can be used in our favour, as well as identifying other ways quantum algorithms can be helpful that is independent of quantum speedups.

16 pages, 8 figures

References in corpus (6)

• Explaining and Harnessing Adversarial Examples
• Delving into Transferable Adversarial Examples and Black-box Attacks
• Adversarial Machine Learning at Scale
• Quantum-state preparation with universal gate decompositions
• Robust data encodings for quantum classifiers
• Quantum statistical query learning

Cited by in corpus (40)

• Solving nonlinear differential equations with differentiable quantum circuits
• Quantum federated learning through blind quantum computing
• Recent advances for quantum classifiers
• Biology and medicine in the landscape of quantum advantages
• Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry
• Towards quantum enhanced adversarial robustness in machine learning
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Generalized quantum circuit differentiation rules
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing
• Robustness Verification of Quantum Classifiers
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Quantum Differentially Private Sparse Regression Learning
• How quantum computing can enhance biomarker discovery
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Privacy-preserving quantum federated learning via gradient hiding
• Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systems
• Training robust and generalizable quantum models
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Ensemble-learning error mitigation for variational quantum shallow-circuit classifiers
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Detecting Violations of Differential Privacy for Quantum Algorithms
• QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
• Investigating the Effect of Noise on the Training Performance of Hybrid Quantum Neural Networks
• Designing Robust Quantum Neural Networks via Optimized Circuit Metrics
• Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing
• Adversarial Robustness Guarantees for Quantum Classifiers
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Maximal Information Leakage from Quantum Encoding of Classical Data
• Mathematical comparison of classical and quantum mechanisms in optimization under local differential privacy
• Quantum Local Differential Privacy and Quantum Statistical Query Model
• Learning Quantum Processes with Quantum Statistical Queries
• Method for noise-induced regularization in quantum neural networks
• Accelerating variational quantum algorithms with multiple quantum processors
• Ensuring superior learning outcomes and data security for authorized learner
• Classical Autoencoder Distillation of Quantum Adversarial Manipulations
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Verifying Adversarial Robustness in Quantum Machine Learning: from theory to physical validation via a software tool
• Quantum-Inspired Weight-Constrained Neural Network: Reducing Variable Numbers by 100x Compared to Standard Neural Networks