Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems (2402.12950v2)

Published 20 Feb 2024 in cs.SE and cs.AI

Abstract: Quantum Neural Network (QNN) combines the Deep Learning (DL) principle with the fundamental theory of quantum mechanics to achieve machine learning tasks with quantum acceleration. Recently, QNN systems have been found to manifest robustness issues similar to classical DL systems. There is an urgent need for ways to test their correctness and security. However, QNN systems differ significantly from traditional quantum software and classical DL systems, posing critical challenges for QNN testing. These challenges include the inapplicability of traditional quantum software testing methods to QNN systems due to differences in programming paradigms and decision logic representations, the dependence of quantum test sample generation on perturbation operators, and the absence of effective information in quantum neurons. In this paper, we propose QuanTest, a quantum entanglement-guided adversarial testing framework to uncover potential erroneous behaviors in QNN systems. We design a quantum entanglement adequacy criterion to quantify the entanglement acquired by the input quantum states from the QNN system, along with two similarity metrics to measure the proximity of generated quantum adversarial examples to the original inputs. Subsequently, QuanTest formulates the problem of generating test inputs that maximize the quantum entanglement adequacy and capture incorrect behaviors of the QNN system as a joint optimization problem and solves it in a gradient-based manner to generate quantum adversarial examples. results demonstrate that QuanTest possesses the capability to capture erroneous behaviors in QNN systems. The entanglement-guided approach proves effective in adversarial testing, generating more adversarial examples.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. 2023. Suppressing quantum errors by scaling a surface code logical qubit. Nature 614, 7949 (2023), 676–681.
  2. Assessing the Effectiveness of Input and Output Coverage Criteria for Testing Quantum Programs. In 2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST). IEEE, 13–23.
  3. Shaukat Ali and Tao Yue. 2023. Quantum Software Testing: A Brief Introduction. In 2023 IEEE/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion). IEEE, 332–333.
  4. Quantum circuits with many photons on a programmable nanophotonic chip. Nature 591, 7848 (2021), 54–60.
  5. Philip Ball. 2021. First 100-QUBIT quantum computer enters crowded race. Nature 599 (2021), 542.
  6. Johannes Bausch. 2020. Recurrent quantum neural networks. Advances in neural information processing systems 33 (2020), 1368–1379. https://doi.org/10.48550/arXiv.2006.14619
  7. Parameterized quantum circuits as machine learning models. Quantum Science and Technology 4, 4 (nov 2019), 043001. https://doi.org/10.1088/2058-9565/ab4eb5
  8. PennyLane: Automatic differentiation of hybrid quantum-classical computations. CoRR abs/1811.04968 (2018). arXiv:1811.04968 http://arxiv.org/abs/1811.04968
  9. Battista Biggio and Fabio Roli. 2018. Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security (Toronto, Canada) (CCS ’18). Association for Computing Machinery, New York, NY, USA, 2154–2156. https://doi.org/10.1145/3243734.3264418
  10. Tensorflow quantum: A software framework for quantum machine learning. arXiv preprint arXiv:2003.02989 (2020).
  11. Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In 2017 ieee symposium on security and privacy (sp). IEEE, 39–57.
  12. Variational quantum algorithms. Nature Reviews Physics 3, 9 (aug 2021), 625–644. https://doi.org/10.1038/s42254-021-00348-9
  13. Quantum convolutional neural networks. Nature Physics 15, 12 (01 Dec 2019), 1273–1278. https://doi.org/10.1038/s41567-019-0648-8
  14. Andrew Cross. 2018. The IBM Q experience and QISKit open-source quantum computing software. In APS March meeting abstracts, Vol. 2018. L58–003.
  15. Cirq Developers. 2023. Cirq. https://doi.org/10.5281/zenodo.8161252
  16. Deepstellar: Model-based quantitative analysis of stateful deep learning systems. In Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 477–487.
  17. Mutation testing of quantum programs written in QISKit. In Proceedings of the ACM/IEEE 44th International Conference on Software Engineering: Companion Proceedings (Pittsburgh, Pennsylvania) (ICSE ’22). Association for Computing Machinery, New York, NY, USA, 358–359. https://doi.org/10.1145/3510454.3528649
  18. QMutPy: a mutation testing tool for Quantum algorithms and applications in Qiskit. In Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2022). Association for Computing Machinery, New York, NY, USA, 797–800. https://doi.org/10.1145/3533767.3543296
  19. Weiyuan Gong and Dong-Ling Deng. 2022. Universal adversarial examples and perturbations for quantum classifiers. National Science Review 9, 6 (2022), nwab130.
  20. Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations. IEEE, New York, NY, USA. https://doi.org/10.48550/arXiv.1412.6572
  21. DLFuzz: Differential Fuzzing Testing of Deep Learning Systems. In Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (Lake Buena Vista, FL, USA). Association for Computing Machinery, New York, NY, USA, 739–743. https://doi.org/10.1145/3236024.3264835
  22. RNN-Test: Towards Adversarial Testing for Recurrent Neural Network Systems. IEEE Trans. Software Eng. 48, 10 (sep 2022), 4167–4180.
  23. Is neuron coverage a meaningful measure for testing deep neural networks?. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ACM, 851–862.
  24. Quantum algorithm for linear systems of equations. Physical review letters 103, 15 (2009), 150502.
  25. Supervised learning with quantum-enhanced feature spaces. Nature 567, 7747 (Mar 2019), 209–212. https://doi.org/10.1038/s41586-019-0980-2
  26. Carl W. Helstrom. 1969. Quantum detection and estimation theory. Journal of Statistical Physics 1, 2 (01 Jun 1969), 231–252. https://doi.org/10.1007/BF01007479
  27. Quantum advantage in learning from experiments. Science 376, 6598 (jun 2022), 1182–1186.
  28. Power of data in quantum machine learning. Nature communications 12, 1 (feb 2021). https://doi.org/10.1038/s41467-021-22539-9
  29. Yipeng Huang and Margaret Martonosi. 2019. Statistical assertions for validating patterns and finding bugs in quantum programs. In Proceedings of the 46th International Symposium on Computer Architecture (ISCA ’19). Association for Computing Machinery, New York, NY, USA, 541–553. https://doi.org/10.1145/3307650.3322213
  30. DeepCrime: mutation testing of deep learning systems based on real faults. In Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis (Virtual, Denmark) (ISSTA 2021). Association for Computing Machinery, New York, NY, USA, 67–78. https://doi.org/10.1145/3460319.3464825
  31. Richard Jozsa. 1994. Fidelity for Mixed Quantum States. Journal of Modern Optics 41, 12 (1994), 2315–2323. https://doi.org/10.1080/09500349414552171 arXiv:https://doi.org/10.1080/09500349414552171
  32. Guiding deep learning system testing using surprise adequacy. In 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE). IEEE, 1039–1049.
  33. Adversarial examples in the physical world. In Artificial intelligence safety and security. Chapman and Hall/CRC, 99–112.
  34. Ryan LaRose and Brian Coyle. 2020. Robust data encodings for quantum classifiers. Phys. Rev. A 102 (sep 2020), 032420. Issue 3. https://doi.org/10.1103/PhysRevA.102.032420
  35. MNIST handwritten digit database. ATT Labs [Online]. Available: http://yann.lecun.com/exdb/mnist (2010).
  36. Projection-based runtime assertions for testing and debugging Quantum programs. Proc. ACM Program. Lang. 4, OOPSLA, Article 150 (nov 2020), 29 pages. https://doi.org/10.1145/3428218
  37. Structural coverage criteria for neural networks could be misleading. In ICSE (NIER) (Montreal, QC, Canada). IEEE / ACM, 89–92. https://doi.org/10.1109/ICSE-NIER.2019.00031
  38. Nana Liu and Peter Wittek. 2020. Vulnerability of quantum classification to adversarial perturbations. Phys. Rev. A 101 (jun 2020), 062331. Issue 6. https://doi.org/10.1103/PhysRevA.101.062331
  39. DeepState: selecting test suites to enhance the robustness of recurrent neural networks. In Proceedings of the 44th International Conference on Software Engineering. 598–609.
  40. Quantum principal component analysis. Nature Physics 10, 9 (2014), 631–633.
  41. Quantum adversarial machine learning. Physical Review Research 2, 3 (jan 2020), 033212. https://doi.org/10.1103/PhysRevResearch.2.033212
  42. DeepCT: Tomographic Combinatorial Testing for Deep Learning Systems. In 26th IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2019, Hangzhou, China, February 24-27, 2019, Xinyu Wang, David Lo, and Emad Shihab (Eds.). IEEE, 614–618. https://doi.org/10.1109/SANER.2019.8668044
  43. Deepgauge: Multi-granularity testing criteria for deep learning systems. In Proceedings of the 33rd ACM/IEEE international conference on automated software engineering. 120–131.
  44. DeepMutation: Mutation Testing of Deep Learning Systems. In 2018 IEEE 29th international symposium on software reliability engineering (ISSRE) (Memphis, TN, USA). IEEE Computer Society, 100–111. https://doi.org/10.1109/ISSRE.2018.00021
  45. PaddlePaddle: An open-source deep learning platform from industrial practice. Frontiers of Data and Domputing 1, 1 (2019), 105–115.
  46. Towards deep learning models resistant to adversarial attacks. (2017). arXiv:arXiv preprint arXiv:1706.06083
  47. Muskit: A mutation analysis tool for quantum software testing. In 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE). IEEE, 1266–1270.
  48. David A. Meyer and Nolan R. Wallach. 2002. Global entanglement in multiparticle systems. J. Math. Phys. 43, 9 (aug 2002), 4273–4278. https://doi.org/10.1063/1.1497700
  49. Andriy Miranskyy and Lei Zhang. 2019. On testing quantum programs. In Proceedings of the 41st International Conference on Software Engineering: New Ideas and Emerging Results (Montreal, Quebec, Canada) (ICSE-NIER ’19). IEEE Press, 57–60. https://doi.org/10.1109/ICSE-NIER.2019.00023
  50. Quantum circuit learning. Phys. Rev. A 98 (sep 2018), 032309. Issue 3. https://doi.org/10.1103/PhysRevA.98.032309
  51. DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks. In CVPR. IEEE Computer Society, 2574–2582.
  52. Noise-Aware Quantum Software Testing. (2023). https://doi.org/10.48550/arXiv.2306.16992 arXiv:arXiv preprint arXiv:2306.16992
  53. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In CVPR. IEEE Computer Society, 427–436.
  54. Michael A Nielsen and Isaac L Chuang. 2010. Quantum computation and quantum information. Cambridge university press. https://doi.org/10.1017/CBO9780511976667
  55. The limitations of deep learning in adversarial settings. In 2016 IEEE European symposium on security and privacy (EuroS&P). IEEE, 372–387.
  56. Crafting adversarial input sequences for recurrent neural networks. In MILCOM 2016-2016 IEEE Military Communications Conference. IEEE, 49–54.
  57. Deepxplore: Automated whitebox testing of deep learning systems. In proceedings of the 26th Symposium on Operating Systems Principles. 1–18.
  58. Absence of Barren Plateaus in Quantum Convolutional Neural Networks. Phys. Rev. X 11 (oct 2021), 041011. Issue 4. https://doi.org/10.1103/PhysRevX.11.041011
  59. Machine learning of high dimensional data on a noisy quantum processor. npj Quantum Information 7, 1 (nov 2021), 161. https://doi.org/10.1038/s41534-021-00498-9
  60. Experimental quantum adversarial learning with programmable superconducting qubits. Nature Computational Science 2, 11 (apr 2022), 711–717. https://doi.org/10.1038/s43588-022-00351-9
  61. Maria Schuld. 2021. Supervised quantum machine learning models are kernel methods. https://doi.org/10.48550/arXiv.2101.11020 arXiv:2101.11020 [quant-ph]
  62. Circuit-centric quantum classifiers. Phys. Rev. A 101 (mar 2020), 032308. Issue 3. https://doi.org/10.1103/PhysRevA.101.032308
  63. Maria Schuld and Francesco Petruccione. 2018. Information Encoding. Springer International Publishing, Cham, 139–171. https://doi.org/10.1007/978-3-319-96424-9_5
  64. Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition. In Proceedings of the 2016 acm sigsac conference on computer and communications security. ACM, 1528–1540.
  65. Parameterized Hamiltonian learning with quantum circuit. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 5 (Aug 2022), 6086–6095.
  66. Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms. Advanced Quantum Technologies 2, 12 (2019), 1900070. https://doi.org/10.1002/qute.201900070
  67. Intriguing properties of neural networks. (2013). https://doi.org/10.48550/arXiv.1312.6199 arXiv:arXiv preprint arXiv:1312.6199
  68. Intriguing properties of neural networks. In ICLR (Poster).
  69. Deeptest: Automated testing of deep-neural-network-driven autonomous cars. In Proceedings of the 40th international conference on software engineering. 303–314.
  70. RobOT: Robustness-oriented testing for deep learning systems. In 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE). IEEE, 300–311.
  71. Adversarial sample detection for deep neural network through model mutation testing. In Proceedings of the 41st International Conference on Software Engineering (Montreal, Quebec, Canada) (ICSE ’19). IEEE Press, 1245–1256. https://doi.org/10.1109/ICSE.2019.00126
  72. Poster: Fuzz testing of quantum program. In 2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST). IEEE, 466–469.
  73. QDiff: differential testing of quantum software stacks. In Proceedings of the 36th IEEE/ACM International Conference on Automated Software Engineering (Melbourne, Australia) (ASE ’21). IEEE Press, 692–704. https://doi.org/10.1109/ASE51524.2021.9678792
  74. Quito: a coverage-guided test generator for quantum programs. In Proceedings of the 36th IEEE/ACM International Conference on Automated Software Engineering (Melbourne, Australia) (ASE ’21). IEEE Press, 1237–1241. https://doi.org/10.1109/ASE51524.2021.9678798
  75. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. CoRR abs/1708.07747 (2017). arXiv:1708.07747 http://arxiv.org/abs/1708.07747
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now