Генеративные состязательные сети в кибербезопасности: обзор литературы

Цели. Основной целью обзора является оценка изменений кибербезопасности и методов обнаружения аномалий в результате действия генеративно-состязательных сетей (ГСС). В исследовании анализируются возможности ГСС при генерации синтетических данных, моделировании состязательных атак, выявлении выбросов, а также решении проблем нестабильности обучения и этических вопросов.
Методы. Проведено систематическое исследование на основе научных статей, охватывающих период с 2014 по 2024 гг.
Результаты. Обсуждение сосредоточено на двух основных областях применения ГСС: обеспечении кибербезопасности посредством обнаружения вторжений и проведения состязательного тестирования, а также обнаружении аномалий в целях медицинской диагностики и мониторинга. Исследованы два ключевых варианта ГСС – вассерштейновские ГСС и условные ГСС – с точки зрения их эффективности в решении технических задач. При оценке качества синтетических данных использованы две метрики: расстояние Фреше и показатель структурного сходства.
Выводы. ГСС улучшают безопасность за счет генерации специализированных наборов данных, что приводит к повышению точности систем обнаружения на 25%. Метод позволяет проводить углубленную состязательную оценку для выявления слабых мест систем, а также способствует обнаружению нарушений в областях с дефицитом данных для медицинской диагностики. Высокоразмерные задачи демонстрируют 40%-ю нестабильность обучения и приводят к 30%-й потере разнообразия выходных данных. ГСС способствуют развитию кибербезопасности и систем обнаружения аномалий, однако остаются вызовы, связанные с обеспечением стабильности обучения, снижением эксплуатационных расходов и соблюдением этических норм, регулирующих их использование. Развитие методов обучения с применением для ГСС и разработка прозрачных систем требуют дальнейших усилий в рамках ответственных инновационных инициатив.

1. Goodfellow I., Pouget-Abadie J., Mirza M., et al. Generative adversarial networks. Commun. ACM. 2020;63(11):139–144. https://doi.org/10.1145/3422622

2. Arifin M.M., Ahmed M.S., Ghosh T.K., Udoy I.A., Zhuang J., Yeh J. A Survey on the Application of Generative Adversarial Networks in Cybersecurity: Prospective. Direction and Open Research Scopes. 2024. ArXiv Prepr. arXiv:2407.08839. https://doi.org/10.48550/arXiv.2407.08839

3. Sabuhi M., Zhou M., Bezemer C.-P., Musilek P. Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review. IEEE Access. 2021;9:161003–161029. https://doi.org/10.1109/ACCESS.2021.3131949

4. Aggarwal A., Mittal V., Battineni G. Generative adversarial network: An overview of theory and applications. Int. J. Inf. Manag. Data Insights. 2021;1(1):100004. https://doi.org/10.1016/j.jjimei.2020.100004

5. Cao Y.-J., Jia L.-L., Chen Y.-X., et al. Recent Advances of Generative Adversarial Networks in Computer Vision. IEEE Access. 2019;7:14985–15006. https://doi.org/10.1109/ACCESS.2018.2886814

6. Radford A., Metz L., Chintala S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. 2016.ArXiv Prepr. arXiv:1511.06434. https://doi.org/10.48550/arXiv.1511.06434

7. Arjovsky M, Chintala S., Bottou L. Wasserstein generative adversarial networks. In: Proceedings of the International Conference on Machine Learning (ICML). PMLR. 2017. P. 214–223. Available from URL: https://proceedings.mlr.press/v70/arjovsky17a/arjovsky17a.pdf

8. Zhu J.-Y., Park T., Isola P., Efros A.A. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. 2020. ArXiv Prepr. arXiv:1703.10593. https://doi.org/10.48550/arXiv.1703.10593

9. Mirza M., Osindero S. Conditional Generative Adversarial Nets. 2014. ArXiv Prepr. arXiv:1411.1784. https://doi.org/10.48550/arXiv.1411.1784

10. Karras T., Laine S., Aila T. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019. P. 4401–4410. https://doi.org/10.1109/CVPR.2019.00453

11. Sedjelmaci H. Attacks detection and decision framework based on generative adversarial network approach: Case of vehicular edge computing network. Trans. Emerg. Telecommun. Technol. 2022;33(10):e4073. https://doi.org/10.1002/ett.4073

12. Kumaran U., Thangam S., Prabhakar T.N., Selvaganesan J., Vishwas H.N. Adversarial Defense: A GAN-IF Based Cybersecurity Model for Intrusion Detection in Software Piracy. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. 2023;14(4):96–114. http://doi.org/10.58346/JOWUA.2023.I4.008

13. Haloui I., Gupta J.S., Feuillard V. Anomaly detection with Wasserstein GAN. 2018. ArXiv Prepr. arXiv:1812.02463. https://doi.org/10.48550/arXiv.1812.02463

14. Kimura D., Chaudhury S., Narita M., Munawar A., Tachibana R. Adversarial Discriminative Attention for Robust Anomaly Detection. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE; 2020. P. 2161–2170. https://doi.org/10.1109/WACV45572.2020.9093428

15. Dunmore A., Jang-Jaccard J., Sabrina F., Kwak J. A Comprehensive Survey of Generative Adversarial Networks (GANs) in Cybersecurity Intrusion Detection. IEEE Access. 2023;11:76071–76094. https://doi.org/10.1109/ACCESS.2023.3296707

16. Kos J., Fischer I., Song D. Adversarial examples for generative models. 2017. ArXiv Prepr. arXiv:1702.06832. https://doi.org/10.48550/arXiv.1702.06832

17. Chhetri S.R., Lopez A.B., Wan J., Al Faruque M.A. GAN-Sec: Generative Adversarial Network Modeling for the Security Analysis of Cyber-Physical Production Systems. In: 2019 Design. Automation & Test in Europe Conference & Exhibition (DATE). IEEE; 2019. P. 770–775. https://doi.org/10.23919/DATE.2019.8715283

18. Mao X., Li Q., Xie H., et al. Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2017. P. 2794–2802. https://doi.org/10.1109/ICCV.2017.304

19. Nataraj L., Karthikeyan S., Jacob G., Manjunath B.S. Malware images: visualization and automatic classification. In: Proceedings of the 8th International Symposium on Visualization for Cyber Security. 2011. P. 1–7. https://doi.org/10.1145/2016904.2016908

20. Chen X., Duan Y., Houthooft R., et al. InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems (NeurIPS). 2016;29:2172–2180.

21. Alo S.O., Jamil A.S., Hussein M.J., Al-Dulaimi M.K.H., Taha S.W., Khlaponina A. Automated Detection of Cybersecurity Threats Using Generative Adversarial Networks (GANs). In: 2024 36th Conference of Open Innovations Association (FRUCT). IEEE. 2024. P. 566–577. https://doi.org/10.23919/FRUCT64283.2024.10749874

22. Zhang J., Li C. Adversarial examples: Opportunities and challenges. IEEE Trans. Neural Netw. Learn. Syst. 2019;31(7): 2578–2593. https://doi.org/10.1109/TNNLS.2019.2933524

23. Zhang S., Xie X., Xu Y. A Brute-Force Black-Box Method to Attack Machine Learning-Based Systems in Cybersecurity. IEEE Access. 2020;8:128250–128263. https://doi.org/10.1109/ACCESS.2020.3008433

24. Papernot N., McDaniel P., Goodfellow I., Jha S., Celik Z.B., Swami A. Practical Black-Box Attacks against Machine Learning. In: Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security. ACM. 2017. P. 506–519. https://doi.org/10.1145/3052973.3053009

25. Kurakin A., Goodfellow I.J., Bengio S. Adversarial examples in the physical world. In book: Artificial Intelligence Safety and Security. Chapman and Hall/CRC. 2018. P. 99–112. https://doi.org/10.1201/9781351251389, Available from URL: https://www.taylorfrancis.com/chapters/edit/10.1201/9781351251389-8/adversarial-examples-physical-world-alexeykurakin-ian-goodfellow-samy-bengio

26. Taheri S., Khormali A., Salem M., Yuan J.-S. Developing a robust defensive system against adversarial examples using generative adversarial networks. Big Data Cogn. Comput. 2020;4(2):11. https://doi.org/10.3390/bdcc4020011

27. Carlini N., Wagner D. Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP). IEEE. 2017. P. 39–57. https://doi.org/10.1109/SP.2017.49

28. Madry A., Makelov A., Schmidt L., Tsipras D., Vladu A. Towards Deep Learning Models Resistant to Adversarial Attacks. 2019. ArXiv Prepr. arXiv:1706.06083. https://doi.org/10.48550/arXiv.1706.06083

29. Sharif M., Bhagavatula S., Bauer L., Reiter M.K. 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. 2016. P. 1528–1540. https://doi.org/10.1145/2976749.2978392

30. Akhtar N., Mian A. Threat of adversarial attacks on deep learning in computer vision: A survey. IEEE Access. 2018;6: 14410–14430. https://doi.org/10.1109/ACCESS.2018.2807385

31. Dong Y., Pang T., Su H., Zhu J. Evading defenses to transferable adversarial examples by translation-invariant attacks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019. P. 4312–4321. Available from URL: http://openaccess.thecvf.com/content_CVPR_2019/html/Dong_Evading_Defenses_to_Transferable_Adversarial_Examples_by_Translation-Invariant_Attacks_CVPR_2019_paper.html

32. Shafahi A., Najibi M., Ghiasi A., et al. Adversarial training for free! Adv. Neural Inf. Process. Syst. 2019:32. Available from URL: https://proceedings.neurips.cc/paper/by-source-2019-1853

33. Xiao C., Li B., Zhu J., He W., Liu M., Song D. Generating Adversarial Examples with Adversarial Networks. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization. 2018. P. 3905–3911. https://doi.org/10.24963/ijcai.2018/543

34. Hou T., Wang T., Lu Z., Liu Y., Sagduyu Y. IoTGAN: GAN powered camouflage against machine learning based IoT device identification. In: 2021 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN). IEEE. 2021. P. 280–287. https://doi.org/10.1109/DySPAN53946.2021.9677264

35. Kurakin A., Goodfellow I., Bengio S. Adversarial examples in the physical world. 2017. ArXiv Prepr. arXiv:1607.02533. https://doi.org/10.48550/arXiv.1607.02533.

36. Goodfellow I., Pouget-Abadie J., Mirza M., et al. Generative adversarial nets. Adv. Neural Inf. Process. Syst. 2014;27. Available from URL: https://proceedings.neurips.cc/paper/5423-generative-adversarial-nets

37. Bengio Y. Learning Deep Architectures for AI. Found. Trends® Mach. Learn. 2009;2(1):1–127. https://doi.org/10.1561/2200000006

38. Isola P., Zhu J.-Y., Zhou T., Efros A.A. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 1125–1134. Available from URL: http://openaccess.thecvf.com/content_cvpr_2017/html/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.html

39. Salimans T., Goodfellow I., Zaremba W., et al. Improved techniques for training GANs. In: Adv. Neural Inf. Process. Syst. (NeurIPS). 2016;29. Available from URL: https://proceedings.neurips.cc/paper_files/paper/2016/hash/8a3363abe792db2d8761d6403605aeb7-Abstract.html

40. Arjovsky M., Bottou L. Towards Principled Methods for Training Generative Adversarial Networks. 2017. ArXiv Prepr. arXiv:1701.04862. https://doi.org/10.48550/arXiv.1701.04862

41. Ho J., Ermon S. Generative adversarial imitation learning. Adv. Neural Inf. Process. Syst. (NeurIPS). 2016;29. Available from URL: https://papers.nips.cc/paper_files/paper/2016/hash/cc7e2b878868cbae992d1fb743995d8f-Abstract.html

42. Mittal S., Joshi A., Finin T. Cyber-All-Intel: An AI for Security related Threat Intelligence. 2019. ArXiv Prepr. arXiv:1905.02895. https://doi.org/10.48550/arXiv.1905.02895

43. Yinka-Banjo C., Ugot O.-A. A review of generative adversarial networks and its application in cybersecurity. Artif. Intell. Rev. 2020;53(3):1721–1736. https://doi.org/10.1007/s10462-019-09717-4

44. Yan Q., Wang M., Huang W., Luo X., Yu F.R. Automatically synthesizing DoS attack traces using generative adversarial networks. Int. J. Mach. Learn. Cybern. 2019;10(12):3387–3396. https://doi.org/10.1007/s13042-019-00925-6

45. Goodfellow I.J., Pouget-Abadie M., Mirza M., et al. Generative adversarial nets. Adv. Neural Inf. Process. Syst. (NeurIPS). 2014;27. Available from URL: https://papers.nips.cc/paper_files/paper/2014/hash/f033ed80deb0234979a61f95710dbe25-Abstract.html

46. Choi Y., Choi M., Kim M., Ha J.-W., Kim S., Choo J. StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE. 2018. P. 8789–8797. https://doi.org/10.1109/CVPR.2018.00916

47. Karras T., Aila T., Laine S., Lehtinen J. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In: International Conference on Learning Representations. 2018. Available from URL: https://research.aalto.fi/en/publications/progressive-growing-of-gans-for-improved-quality-stability-and-va

48. Brock A., Donahue J., Simonyan K. Large Scale GAN Training for High Fidelity Natural Image Synthesis. In: International Conference on Learning Representations. 2018. https://doi.org/10.48550/arXiv.1809.11096

49. Wang T.-C., Liu M.-Y., Zhu J.-Y., Tao A., Kautz J., Catanzaro B. High-resolution image synthesis and semantic manipulation with conditional gans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. P. 8798–8807. Available from URL: http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_High-Resolution_Image_Synthesis_CVPR_2018_paper.html

50. Li C., Wand M. Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks. In: Leibe B., Matas J., Sebe N., Welling M. (Eds.). Computer Vision – ECCV 2016. Series: Lecture Notes in Computer Science. Cham: Springer; 2016. V. 9907. P. 702–716. https://doi.org/10.1007/978-3-319-46487-9_43

51. Mirsky Y., Lee W. The Creation and Detection of Deepfakes: A Survey. ACM Comput. Surv. Jan. 2022;54(1):1–41. https://doi.org/10.1145/3425780

52. Odena A., Olah C., Shlens J. Conditional image synthesis with auxiliary classifier GANs. In: Proceedings of the 34th International Conference on Machine Learning (ICML). PMLR. 2017. P. 2642–2651. Available from URL: https://proceedings.mlr.press/v70/odena17a.html

53. Wang Z., She Q., Ward T.E. Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy. ACM Comput. Surv. 2022;54(2):1–38. https://doi.org/10.1145/3439723

54. Creswell A., White T., Dumoulin V., Arulkumaran K., Sengupta B., Bharath A.A. Generative Adversarial Networks: An Overview. IEEE Signal Process. Mag. 2018;35(1):53–65. https://doi.org/10.1109/MSP.2017.2765202

55. Zhang H., Goodfellow I., Metaxas L., et al. Self-attention generative adversarial networks. In: Proceedings of the 36th International Conference on Machine Learning (ICML). PMLR. 2019. P. 7354–7363. Available from URL: https://proceedings.mlr.press/v97/zhang19d.html

56. Lucic M., Kurach K., Michalski M., Gelly S., Bousquet O. Are gans created equal? A large-scale study. Adv. Neural Inf. Process. Syst. (NeurIPS) 2018;31. Available from URL: https://proceedings.neurips.cc/paper/2018/hash/e46de7e1bcaaced9a54f1e9d0d2f800d-Abstract.html

57. Sun H., Zhu T., Zhang Z., Xiong D.J.P., Zhou W. Adversarial Attacks Against Deep Generative Models on Data: A Survey. IEEE Trans. Knowl. Data Eng. 2023;35(4):3367–3388. https://doi.org/10.1109/TKDE.2021.3130903

58. Miyato T., Kataoka T., Koyama M., Yoshida Y. Spectral Normalization for Generative Adversarial Networks. 2018. ArXiv Prepr. arXiv:1802.05957. https://doi.org/10.48550/arXiv.1802.05957

59. Che T., Li Y., Jacob A.P., Bengio Y., Li W. Mode Regularized Generative Adversarial Networks. 2017. ArXiv Prepr. arXiv:1612.02136. https://doi.org/10.48550/arXiv.1612.02136

60. Bao J., Chen D., Wen F., Li H., Hua G. CVAE-GAN: Fine-Grained Image Generation Through Asymmetric Training. Presented at the Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2017. P. 2745–2754. Available from URL: https://openaccess.thecvf.com/content_iccv_2017/html/Bao_CVAE-GAN_Fine-Grained_Image_ICCV_2017_paper.html

61. Westerlund M. The emergence of deepfake technology: A review. Technol. Innov. Manag. Rev. 2019;9(11):39–52.

62. Tolosana R., Vera-Rodriguez R., Fierrez J., Morales A., Ortega-Garcia J. Deepfakes and beyond: A survey of face manipulation and fake detection. Inf. Fusion. 2020;64:131–148. https://doi.org/10.1016/j.inffus.2020.06.014

63. Zhao J. Energy-based Generative Adversarial Network. 2016. ArXiv Prepr. arXiv:1609.03126. https://doi.org/10.48550/arXiv.1609.03126

64. Reed S., Akata Z., Yan X., Logeswaran L., Schiele B., Lee H. Generative adversarial text to image synthesis. In: Proceedings of the 33th International Conference on Machine Learning. PMLR. 2016. P. 1060–1069. Available from URL: http://proceedings.mlr.press/v48/reed16.html

65. Lloyd S., Weedbrook C. Quantum Generative Adversarial Learning. Phys. Rev. Lett. 2018;121(4):040502. https://doi.org/10.1103/PhysRevLett.121.040502

66. Gulrajani I., Ahmed F., Arjovsky M., Dumoulin V., Courville A.C. Improved training of wasserstein gans. Adv. Neural Inf. Process. Syst. 2017;30. Available from URL: https://proceedings.neurips.cc/paper/2017/hash/892c3b1c6dccd52936e27cbd0ff683d6-Abstract.html

67. Park T., Liu M.-Y., Wang T.-C., Zhu J.-Y. Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019. P. 2337–2346. Available from URL: http://openaccess.thecvf.com/content_CVPR_2019/html/Park_Semantic_Image_Synthesis_With_Spatially-Adaptive_Normalization_CVPR_2019_paper.html

68. Hoang Q., Nguyen T.D., Le T., Phung D. MGAN: Training Generative Adversarial Nets with Multiple Generators. 2018.

69. Hitaj B., Gasti P., Ateniese G., Perez-Cruz F. PassGAN: A Deep Learning Approach for Password Guessing. 2019. ArXiv Prepr. arXiv:1709.00440. https://doi.org/10.48550/arXiv.1709.00440

70. Sharma Y., Ding G.W., Brubaker M. On the Effectiveness of Low Frequency Perturbations. 2019. ArXiv Prepr. arXiv:1903.00073. https://doi.org/10.48550/arXiv.1903.00073

71. Zhang C., Yu S., Tian Z., Yu J.J.Q. Generative Adversarial Networks: A Survey on Attack and Defense Perspective. ACM Comput. Surv. 2024;56(4):1–35. https://doi.org/10.1145/3615336

72. Zhang J., Zhao L., Yu K., Min G., Al-Dubai A.Y., Zomaya A.Y. A Novel Federated Learning Scheme for Generative Adversarial Networks. IEEE Trans. Mob. Comput. 2024;23(5):3633–3649. https://doi.org/10.1109/TMC.2023.3278668

73. Kaviani S., Han K.J., Sohn I. Adversarial attacks and defenses on AI in medical imaging informatics: A survey. Expert Syst. Appl. 2022;198:116815. https://doi.org/10.1016/j.eswa.2022.116815

74. Ribeiro M.T., Singh S., Guestrin C. Why Should I Trust You? Explaining the Predictions of Any Classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA. 2016. P. 1135–1144. https://doi.org/10.1145/2939672.2939778

75. Zhang Q., Wu Y.N., Zhu S.-C. Interpretable convolutional neural networks. In: Proceedings of the IEEE/CVPR Conference on Computer Vision and Pattern Recognition. 2018. P. 8827–8836. https://doi.org/10.1109/CVPR.2018.00920

76. Borji A. Pros and Cons of GAN Evaluation Measures. 2018. ArXiv Prepr. arXiv:1802.03446. https://doi.org/10.48550/arXiv.1802.03446

77. Yang Y., Li Y., Zhang W., Qin F., Zhu P., Wang C.-X. Generative-Adversarial-Network-Based Wireless Channel Modeling: Challenges and Opportunities. IEEE Commun. Mag. 2019;57(3):22–27. https://doi.org/10.1109/MCOM.2019.1800635

78. Li T., Zhang S., Xia J. Quantum generative adversarial network: A survey. Comput. Mater. Contin. 2020;64(1):401–438. https://doi.org/10.32604/cmc.2020.010551

79. Zhao S., Liu Z., Lin J., Zhu J.-Y., Han S. Differentiable augmentation for data-efficient GAN training. Adv. Neural Inf. Process. Syst. 2020;33:7559–7570. Available from URL: https://proceedings.neurips.cc/paper/2020/hash/55479c55ebd1efd3ff125f1337100388-Abstract.html

80. Mittelstadt B., Russell C., Wachter S. Explaining Explanations in AI. In: Proceedings of the Conference on Fairness. Accountability. and Transparency. Atlanta, GA, USA. 2019. P. 279–288. https://doi.org/10.1145/3287560.3287574