Abstract
Quantum Machine Learning (QML) is a new discipline that combines quantum computing and machine learning algorithms in order to take advantage of the computational benefits which are provided by quantum computing for performing complex problems. While similar to classical machine learning systems, quantum-models tend to be prone for adversarial attacks—craft perturbations designed purposely for causing model mispredictions. The intrinsic noise and probabilistic behavior of quantum systems— in particular the (Noisy Intermediate-Scale Quantum) NISQ—is only worsening these vulnerabilities. This paper provides an overview of adversarial threats in QML and illustrates how the quantum nature of any specific system to be attacked shapes both attack and defence strategies.
We study on prevalent adversarial methods including gradient based perturbations, optimization attacks and transfer attacks among others, for their resonance in the quantum settings. And, we explore the influence of quantum noise, circuit layout, and hybrid architectures on system weaknesses. In order to develop solutions for such problems, we provide a survey of defines approaches including adversarial training noise-aware learning quantum error mitigation and robust optimization By incorporating probabilistic approaches like Bayesian inference, the ability to make decisions with uncertainty informs and strengthens resilience. Fields like cybersecurity, healthcare and autonomous systems showcase implications of adversarial robustness in QML. Lastly, the paper presents open challenges and future directions for research where some of them are on building scalable secured interpretable quantum AI systems.
Reference
[1] Sutton, R.S. and Barton, A.G. (2018) Reinforcement Learning: An Introduction. 2nd end. Cambridge, MA: MIT Press.
[2] Sutton, R.S. (1988) ‘Learning to predict by the methods of temporal differences’, Machine Learning, 3(1), pp. 9–44.
[3] Barton, A.G. (1995) ‘Reinforcement learning in neural networks’.
[4] Goldberg, D.E. (1989) Genetic Algorithms in Search, Optimization and Machine Learning. Reading, MA: Addison-Wesley.
[5] Holland, J.H. (1992) Adaptation in Natural and Artificial Systems. Cambridge, MA: MIT Press.
[6] Stanley, K.O. and Miikkulainen, R. (2002) ‘Evolving neural networks through augmenting topologies’, Evolutionary Computation.
[7] Back, T. (1996) Evolutionary Algorithms in Theory and Practice. Oxford: Oxford University Press.
[8] Hansen, N. (2006) ‘The CMA evolution strategy’.
[9] Lloyd, S. (2013) Quantum machine learning. ArXiv:1307.0411.
[10] Belmonte, J. et al. (2017) ‘Quantum machine learning’, Nature, 549, pp. 195–202.
[11] Schulz, M. and Petruccione, F. (2018) Supervised Learning with Quantum Computers. Cham: Springer.
[12] Carazo, M. et al. (2021) ‘Variational quantum algorithms’, Nature Reviews Physics.
[13] McLean, J.R. et al. (2018) ‘Barren plateaus in quantum neural network training landscapes’, Nature Communications.
[14] Farsi, E. et al. (2014) A quantum approximate optimization algorithm. arrive.
[15] Rebentrost, P. et al. (2014) ‘Quantum support vector machine for big data classification’, Physical Review Letters.
[16] Havelock, V. et al. (2019) ‘Supervised learning with quantum-enhanced feature spaces’, Nature.
[17] Mitral, K. et al. (2018) ‘Quantum circuit learning’, Physical Review A.
[18] Benedetti, M. et al. (2019) ‘Parameterized quantum circuits as machine learning models’, Quantum Science and Technology.
[19] Reskill, J. (2018) ‘Quantum computing in the NISQ era and beyond’, Quantum, 2, p.79.
[20] Nielsen, M.A. and Chuang, I.L. (2010) Quantum Computation and Quantum Information. Cambridge: Cambridge University Press.
[21] Grover, L.K. (1996) ‘A fast quantum mechanical algorithm for database search’.
[22] Short, P.W. (1994) ‘Algorithms for quantum computation: discrete logarithms and factoring’.
[23] Harrow, A.W. et al. (2009) ‘Quantum algorithm for linear systems of equations’.
[24] Gateman, D. (2010) ‘An introduction to quantum error correction’.
[25] Endo, S. et al. (2018) ‘Practical quantum error mitigation’, Physical Review X.
[26] Time, K. et al. (2017) ‘Error mitigation for short-depth quantum circuits’.
[27] Aaronson, S. (2013) Quantum Computing since Democritus. Cambridge: Cambridge University Press.
[28] Atreus, J. (2018) the Theory of Quantum Information. Cambridge: Cambridge University Press.
[29] Murphy, K.P. (2012) Machine Learning: A Probabilistic Perspective. MIT Press.
[30] Bishop, C.M. (2006) Pattern Recognition and Machine Learning. New York: Springer.
[31] Good fellow, I., Bagnio, Y. and Carville, A. (2016) Deep Learning. MIT Press.
[32] Gal, Y. (2016) Uncertainty in Deep Learning. PhD Thesis, University of Cambridge.
[33] Rasmussen, C.E. and Williams, C.K.I. (2006) Gaussian Processes for Machine Learning. MIT Press.
[34] Huller Meier, E. and Aegean, W. (2021) ‘Aleatoric and epistemic uncertainty in machine learning’, Machine Learning.
[35] IBM Quantum (2025) Quantum computing research.
[36] Google Quantum AI (2024) Quantum AI advancements.
[37] Microsoft Quantum (2025) Quantum development tools.
[38] Regatta computing (2024) Hybrid quantum systems.
[39] Landau (2024) Photonic quantum computing.
[40] Schmidhuber, J. (2015) ‘Deep learning overview’, Neural Networks.
[41] Minho, V. et al. (2015) ‘Human-level control through deep reinforcement learning’, Nature.
[42] Silver, D. et al. (2016) ‘Mastering the game of Go with deep neural networks and tree search’, Nature.
[43] Levine, S. (2018) ‘Deep reinforcement learning overview’.
[44] Finn, C. et al. (2017) ‘Model-agnostic meta-learning for fast adaptation of deep networks’.
[45] Kingma, D.P. and Welling, M. (2014) ‘Auto-encoding Variational Bayes’.