A review of generative adversarial networksfor security applications

• Autorzy: Rayavarapu, Swarajya Madhuri , Tammineni, Shanmukha Prasanthi , Gottapu, Sasibhushana Rao , Singam, Aruna

Warianty tytułu

PL

Przegląd generatywnych sieci przeciwstawnych dla zastosowań bezpieczeństwa

• Języki publikacji: EN

Abstrakty

EN

Advances in cybersecurity are crucial for a country's economic and national security. As data transmission and storage exponentially increase, new threat detection and mitigation techniques are urgently needed. Cybersecurity has become an absolute necessity, with the ever-increasing transmitted networks from day to day causing exponential growth of data that is being stored on servers. In order to thwart sophisticatedattacks in the future, it willbe necessary to regularly update threat detection and data preservation techniques. Generative adversarial networks (GANs) are a class of unsupervised machine learning models that can generate synthetic data. GANs are gaining importance in AI-based cybersecurity systems for applications suchas intrusion detection, steganography, cryptography, and anomaly detection. This paper provides a comprehensive review of research on applying GANs for cybersecurity, including an analysis of popular cybersecurity datasets and GAN model architectures used in these studies.

PL

Postępy w cyberbezpieczeństwie mają kluczowe znaczenie dla bezpieczeństwa gospodarczego i narodowego kraju. Ponieważ transmisja i przechowywanie danych gwałtownie rośnie, pilnie potrzebne są nowe techniki wykrywania i łagodzenia zagrożeń. Cyberbezpieczeństwo stało się absolutną koniecznością, ponieważ stale rosnąca liczba przesyłanych sieci z dnia na dzień powoduje wykładniczy wzrost danych przechowywanych na serwerach. Aby w przyszłości udaremnić wyrafinowane ataki, konieczna będzie regularna aktualizacja technik wykrywania zagrożeń i zabezpieczania danych. Generatywne sieci przeciwstawne (GAN) to klasa modeli uczenia maszynowego bez nadzoru, które mogą generować dane syntetyczne. Sieci GAN zyskują na znaczeniu w systemach cyberbezpieczeństwa opartych na sztucznej inteligencji do zastosowań takich jak wykrywanie włamań, steganografia, kryptografia i wykrywanie anomalii. W artykule dokonano kompleksowego przeglądu badań nad zastosowaniem sieci GAN do celów cyberbezpieczeństwa, w tym analizę popularnych zbiorów danych dotyczących cyberbezpieczeństwa oraz architektur modeli GAN wykorzystanych w tych badaniach.

Słowa kluczowe

PL

model generatywny; cyberbezpieczeństwo; uczenie maszynowe; sieci neuronowe; uczenie się bez nadzoru

EN

generative model; cyber security; machine learning; neural networks; unsupervised learning

• Czasopismo: Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
• Rocznik: 2024
• Tom: T. 14, nr 2
• Strony: 66--70
• Opis fizyczny: Bibliogr. 32 poz., fot., tab., wykr.

Twórcy

autor

Rayavarapu, Swarajya Madhuri

• Andhra University, Department of Electronics and Communication Engineering, Visakhapatnam,India,

autor

Tammineni, Shanmukha Prasanthi

• Andhra University, Department of Electronics and Communication Engineering, Visakhapatnam, India,

autor

Gottapu, Sasibhushana Rao

• Andhra University, Department of Electronics and Communication Engineering, Visakhapatnam,India,

autor

Singam, Aruna

• Andhra University, Department of Electronics and Communication Engineering, Visakhapatnam,India,

Bibliografia

• [1] Abadi M., Andersen D. G..: Learning to Protect Communications with Adversarial Neural Cryptography. 2016 [http://arxiv.org/abs/1610.06918].
• [2] Araba Vander–Pallen M. et al.: Survey on Types of Cyber Attacks on Operating System Vulnerabilities since 2018 Onwards. IEEE World AI IoT Congress – AIIoT, 2022, 01–07 [https://doi.org/10.1109/AIIoT54504.2022.9817246].
• [3] Creech G., Hu J.: A Semantic Approach to Host-Based Intrusion Detection Systems Using Contiguousand Discontiguous System Call Patterns. IEEE Transactions on Computers 63(4), 2014, 807–819 [https://doi.org/10.1109/TC.2013.13].
• [4] Creech G., Hu J.: Generation of a New IDS Test Dataset: Time to Retire the KDD Collection. IEEE Wireless Communications and Networking Conference – WCNC, 2013 [https://doi.org/10.1109/wcnc.2013.6555301].
• [5] Creech G.: Developing a High-Accuracy Cross Platform Host-Based Intrusion Detection System Capable of Reliably Detecting Zero-Day Attacks. 2014.
• [6] Dash A. et al.: A Review of Generative Adversarial Networks (GANs) and Its Applications in a Wide Variety of Disciplines - From Medical to Remote Sensing, 2021 [http://arxiv.org/abs/2110.01442].
• [7] Deng Li.: The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]. IEEE Signal Processing Magazine 29(6), 2012, 141–142 [https://doi.org/10.1109/MSP.2012.2211477].
• [8] Gomez A. N. et al.: Unsupervised Cipher Cracking Using Discrete GANs, 2018 [http://arxiv.org/abs/1801.04883].
• [9] Goodfellow I. J. et al.: Generative Adversarial Networks. arXiv [Stat.ML], 2014 [http://arxiv.org/abs/1406.2661].
• [10] Hitaj B. et al.: PassGAN: A Deep Learning Approach for Password Guessing. ACNS. 2019.
• [11] Khelifi L., Mignotte M.: Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis. IEEE Access 8, 2020, 126385–126400 [https://doi.org/10.1109/ACCESS.2020.3008036].
• [12] Kumar S. et al.: Research Trends in Network-Based Intrusion Detection Systems: A Review. IEEE Access 9, 2021, 157761–157779 [https://doi.org/10.1109/ACCESS.2021.3129775].
• [13] Learned-Miller G. B. H. E.: Labeled Faces in the Wild: Updates and New Reporting Procedures. University of Massachusetts. 2014.
• [14] Lin Z. et al.: IDSGAN: Generative Adversarial Networks for Attack Generation Against Intrusion Detection. Lecture Notes in Computer Science, Springer International Publishing, 2022, 79–91 [https://doi.org/10.1007/978-3-031- 05981-0_7].
• [15] Liu Z. et al.: Deep Learning Face Attributes in the Wild. IEEE International Conference on Computer Vision – ICCV, IEEE, 2015 [https://doi.org/10.1109/iccv.2015.425].
• [16] Moustafa N., Slay J.: The Evaluation of Network Anomaly Detection Systems: Statistical Analysis of the UNSW-NB15 Data Set and the Comparison with the KDD99 Data Set. Information Security Journal A Global Perspective 25(1–3), 2016, 18–31 [https://doi.org/10.1080/19393555.2015.1125974].
• [17] Nam S. et al.: Recurrent GANs Password Cracker for IoT Password Security Enhancement. Sensors (Basel, Switzerland) 20(11), 3106 [https://doi.org/10.3390/s20113106].
• [18] Odena A. et al.: Conditional Image Synthesis With Auxiliary Classifier GANs. 2016 [https://doi.org/10.48550].
• [19] Radford A. et al.: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. 2016 [http://arxiv.org/abs/1511.06434].
• [20] Schlegl Th. et al.: Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery. 2017 [http://arxiv.org/abs/1703.05921].
• [21] Sharafaldin I. et al.: Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization. 4th International Conference on Information Systems Security and Privacy (ICISSP), 2018.
• [22] Shen Y. et al.: Gan-Based Garment Generation Using Sewing Pattern Images. European Conference on Computer Vision, Springer, 225–247.
• [23] Subramanian, N. et al.: Image Steganography: A Review of the Recent Advances. IEEE Access: Practical Innovations, Open Solutions 9, Institute of Electrical and Electronics Engineers (IEEE), 2021, 23409–23423 [https://doi.org/10.1109/access.2021.3053998].
• [24] Tavallaee, M. et al.: A Detailed Analysis of the KDD CUP 99 Data Set. IEEE Symposium on Computational Intelligence for Security and Defense Applications, IEEE, 2009 [https://doi.org/10.1109/cisda.2009.5356528].
• [25] Tong K. et al.: Recent Advances in Small Object Detection Based on Deep Learning: A Review. Image and Vision Computing 97, 2020, 103910 [https://doi.org/10.1016/j.imavis.2020.103910].
• [26] Volkhonskiy Denis et al.: Steganographic Generative Adversarial Networks. 2019 [http://arxiv.org/abs/1703.05502].
• [27] Wu Ch. et al.: WGAN-E: A Generative Adversarial Networks for Facial Feature Security. Electronics 9(3), 2020, 486 [https://doi.org/10.3390/electronics9030486].
• [28] Yang J. et al.: Spatial Image Steganography Based on Generative Adversarial Network, 2018 [http://arxiv.org/abs/1804.07939].
• [29] Yang Y. et al.: GAN-Based Semi-Supervised Learning Approach for Clinical Decision Support in Health-IoT Platform. IEEE Access 7, 2019, 8048–8057 [https://doi.org/10.1109/ACCESS.2018.2888816].
• [30] Zenati H. et al.: Efficient GAN-Based Anomaly Detection. 2019. [http://arxiv.org/abs/1802.06222].
• [31] Zheng W. et al.: GAN-Based Key Secret-Sharing Scheme in Blockchain. IEEE Transactions on Cybernetics 51(1), 2021, 393–404 [https://doi.org/10.1109/TCYB.2019.2963138].
• [32] Zhu J. Y. et al. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks, 2017 [https://doi.org/10.48550/ARXIV.1703.10593].

Identyfikatory

DOI

10.35784/iapgos.5778