Controlled Steering-Based State Preparation for Adversarial-Robust Quantum Machine Learning

• URL: http://arxiv.org/abs/2605.10954v1
• Date: Thu, 30 Apr 2026 16:15:40 GMT
• Title: Controlled Steering-Based State Preparation for Adversarial-Robust Quantum Machine Learning
• Abstract summary: Quantum machine learning (QML) provides a promising framework for leveraging quantum-mechanical effects in learning tasks.<n>Small perturbations applied to classical inputs can propagate through the quantum encoding stage and distort the resulting quantum state.<n>We propose a defense mechanism that replaces the conventional quantum encoding stage of a QML model with passive steering-based controlled state preparation.
• Score: 2.175752761257231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum machine learning (QML) provides a promising framework for leveraging quantum-mechanical effects in learning tasks. However, its vulnerability to adversarial perturbations remains a major challenge for practical deployment. In QML systems, small perturbations applied to classical inputs can propagate through the quantum encoding stage and distort the resulting quantum state, thereby degrading model performance. In this work, we propose a defense mechanism that replaces the conventional quantum encoding stage of a QML model with passive steering-based controlled state preparation, which guides the encoded state toward a controlled intermediate state. By tuning the steering strength and the number of steering iterations, the proposed method suppresses the influence of adversarial perturbations while maintaining high clean accuracy and improving adversarial accuracy. Experimental results demonstrate that the passive steering-based defense consistently improves adversarial accuracy across different QML models and datasets under gradient-based adversarial attacks, achieving adversarial accuracy improvements of up to 40.19%.

Related papers

• Machine Learning Techniques for Enhancing Quantum Key Distribution [0.0]
  Quantum Key Distribution (QKD) offers theoretically unbreakable security by leveraging quantum mechanics.<n>Practical implementation is challenged by environmental vulnerabilities, noise, and hardware imperfections.<n>Recent Machine Learning (ML) has emerged as a powerful tool to address these limitations and enhance the real-world viability of QKD systems.
  arXiv  Detail & Related papers  (2026-03-07T23:51:47Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Reinforcement Learning Control of Quantum Error Correction [108.70420561323692]
  Quantum computer learns to self-improve directly from its errors and never stops computing.<n>This work enables a new paradigm: a quantum computer that learns to self-improve directly from its errors and never stops computing.
  arXiv  Detail & Related papers  (2025-11-11T17:32:25Z)
• Autonomous Floquet Engineering of Bosonic Codes via Reinforcement Learning [4.78580425445851]
  Bosonic codes represent a promising route toward quantum error correction in continuous-variable computation systems.<n>We introduce a reinforcement-learning-assisted Floquet engineering approach for the autonomous preparation of bosonic codes that is general, efficient, and noise-resilient.
  arXiv  Detail & Related papers  (2025-10-25T09:14:55Z)
• End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost [53.25965863436039]
  Quantization-aware training (QAT) provides a more principled solution, but its reliance on backpropagation incurs prohibitive memory costs.<n>We propose ZeroQAT, a zeroth-order optimization-based QAT framework that supports both weight and activation quantization.<n>Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory.
  arXiv  Detail & Related papers  (2025-08-21T01:18:27Z)
• Fooling the Decoder: An Adversarial Attack on Quantum Error Correction [49.48516314472825]
  In this work, we target a basic RL surface code decoder (DeepQ) to create the first adversarial attack on quantum error correction.<n>We demonstrate an attack that reduces the logical qubit lifetime in memory experiments by up to five orders of magnitude.<n>This attack highlights the susceptibility of machine learning-based QEC and underscores the importance of further research into robust QEC methods.
  arXiv  Detail & Related papers  (2025-04-28T10:10:05Z)
• Variational Quantum Machine Learning with Quantum Error Detection [0.6435156676256051]
  Quantum machine learning (QML) is an emerging field that promises advantages such as faster training, improved reliability and superior extraction over classical counterparts.<n>Its implementation on quantum hardware is challenging due to the noise inherent in these systems, necessitating the use of quantum error correction (QEC) codes.<n>Current QML research remains primarily theoretical, often assuming noise-free environments and offering little insight into the integration of QEC with QML.
  arXiv  Detail & Related papers  (2025-04-09T10:56:21Z)
• Computable Model-Independent Bounds for Adversarial Quantum Machine Learning [4.857505043608425]
  We introduce the first of an approximate lower bound for adversarial error when evaluating model resilience against quantum-based adversarial attacks. In the best case, the experimental error is only 10% above the estimated bound, offering evidence of the inherent robustness of quantum models.
  arXiv  Detail & Related papers  (2024-11-11T10:56:31Z)
• GQHAN: A Grover-inspired Quantum Hard Attention Network [53.96779043113156]
  Grover-inspired Quantum Hard Attention Mechanism (GQHAM) is proposed. GQHAN adeptly surmounts the non-differentiability hurdle, surpassing the efficacy of extant quantum soft self-attention mechanisms. The proposal of GQHAN lays the foundation for future quantum computers to process large-scale data, and promotes the development of quantum computer vision.
  arXiv  Detail & Related papers  (2024-01-25T11:11:16Z)
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning [0.5181797490530444]
  We implement methods for the efficient preparation of quantum states representing encoded image data using variational, genetic and matrix product state based algorithms. 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.
  arXiv  Detail & Related papers  (2023-09-18T01:49:36Z)
• Towards Accurate Post-Training Quantization for Vision Transformer [48.779346466374406]
  Existing post-training quantization methods still cause severe performance drops. APQ-ViT surpasses the existing post-training quantization methods by convincing margins.
  arXiv  Detail & Related papers  (2023-03-25T03:05:26Z)
• Potential and limitations of quantum extreme learning machines [55.41644538483948]
  We present a framework to model QRCs and QELMs, showing that they can be concisely described via single effective measurements. Our analysis paves the way to a more thorough understanding of the capabilities and limitations of both QELMs and QRCs.
  arXiv  Detail & Related papers  (2022-10-03T09:32:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.