{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T19:11:34Z","timestamp":1721934694573},"reference-count":31,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,2,5]],"date-time":"2022-02-05T00:00:00Z","timestamp":1644019200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Science and Higher Education of Russia","award":["FEWM-2020-0037 (TUSUR)"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"Machine learning algorithms based on neural networks are vulnerable to adversarial attacks. The use of attacks against authentication systems greatly reduces the accuracy of such a system, despite the complexity of generating a competitive example. As part of this study, a white-box adversarial attack on an authentication system was carried out. The basis of the authentication system is a neural network perceptron, trained on a dataset of frequency signatures of sign. For an attack on an atypical dataset, the following results were obtained: with an attack intensity of 25%, the authentication system availability decreases to 50% for a particular user, and with a further increase in the attack intensity, the accuracy decreases to 5%.<\/jats:p>","DOI":"10.3390\/info13020077","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T01:36:47Z","timestamp":1644197807000},"page":"77","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Attacks Impact on the Neural Network Performance and Visual Perception of Data under Attack"],"prefix":"10.3390","volume":"13","author":[{"given":"Yakov","family":"Usoltsev","sequence":"first","affiliation":[{"name":"Faculty of Security, Tomsk State University of Control Systems and Radioelectronics, 40 Lenin Avenue, 634050 Tomsk, Russia"}]},{"given":"Balzhit","family":"Lodonova","sequence":"additional","affiliation":[{"name":"Faculty of Security, Tomsk State University of Control Systems and Radioelectronics, 40 Lenin Avenue, 634050 Tomsk, Russia"}]},{"given":"Alexander","family":"Shelupanov","sequence":"additional","affiliation":[{"name":"Faculty of Security, Tomsk State University of Control Systems and Radioelectronics, 40 Lenin Avenue, 634050 Tomsk, Russia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3222-9956","authenticated-orcid":false,"given":"Anton","family":"Konev","sequence":"additional","affiliation":[{"name":"Faculty of Security, Tomsk State University of Control Systems and Radioelectronics, 40 Lenin Avenue, 634050 Tomsk, Russia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8000-2716","authenticated-orcid":false,"given":"Evgeny","family":"Kostyuchenko","sequence":"additional","affiliation":[{"name":"Faculty of Security, Tomsk State University of Control Systems and Radioelectronics, 40 Lenin Avenue, 634050 Tomsk, Russia"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1750025","DOI":"10.1142\/S0218348X17500256","article-title":"A Review on State-of-the-Art Face Recognition Approaches","volume":"25","author":"Mahmood","year":"2017","journal-title":"Fractals"},{"key":"ref_2","first-page":"95","article-title":"A Review on Authentication Methods","volume":"7","author":"Idrus","year":"2013","journal-title":"Aust. J. Basic Appl. Sci."},{"key":"ref_3","first-page":"3","article-title":"Random Keypad and Face Recognition Authentication Mechanism","volume":"5","author":"Shukla","year":"2018","journal-title":"Int. Res. J. Eng. Technol. (IRJET)"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1109\/TSP.2004.839903","article-title":"User Authentication through Typing Biometrics Features","volume":"53","author":"Araujo","year":"2005","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1016\/j.comcom.2019.12.016","article-title":"AFA: Adversarial fingerprinting authentication for deep neural networks","volume":"150","author":"Zhao","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_6","first-page":"61","article-title":"Development of Face and Signature Fusion Technology for Biometrics Authentication","volume":"6","author":"Shinde","year":"2018","journal-title":"Int. J. Emerg. Res. Manag. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1007\/s12652-019-01437-5","article-title":"A Fingerprint Based Crypto-Biometric System for Secure Communication","volume":"11","author":"Dwivedi","year":"2020","journal-title":"J. Ambient. Intell. Hum. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TSUSC.2018.2793466","article-title":"An Encryption Approach Using Information Fusion Techniques Involving Prime Numbers and Face Biometrics","volume":"5","author":"Iovane","year":"2020","journal-title":"IEEE Trans. Sustain. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/0262-8856(95)99726-H","article-title":"Automatic Face Identification System Using Flexible Appearance Models","volume":"13","author":"Lanitis","year":"1995","journal-title":"Image Vis. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"596","DOI":"10.18287\/2412-6179-CO-621","article-title":"Automatic text-independent speaker verification using convolutional deep belief network","volume":"44","author":"Rakhmanenko","year":"2020","journal-title":"Comput. Opt."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chandankhede, P.H., Titarmare, A.S., and Chauhvan, S. (2021, January 19\u201320). Voice Recognition Based Security System Using Convolutional Neural Network. Proceedings of the 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), Greater Noida, India.","DOI":"10.1109\/ICCCIS51004.2021.9397151"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, X., Xiong, Q., Dai, Y., and Xu, X. (2018, January 7\u201310). Voice Biometric Identity Authentication System Based on Android Smart Phone. Proceedings of the 2018 IEEE 4th International Conference on Computer and Communications (ICCC), Chengdu, China.","DOI":"10.1109\/CompComm.2018.8780990"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Boles, A., and Rad, P. (2017, January 18\u201321). Voice Biometrics: Deep Learning-Based Voiceprint Authentication System. Proceedings of the 2017 12th System of Systems Engineering Conference (SoSE), Waikoloa, HI, USA.","DOI":"10.1109\/SYSOSE.2017.7994971"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"16345","DOI":"10.1007\/s11042-018-7012-3","article-title":"Multimodal Biometric Scheme for Human Authentication Technique Based on Voice and Face Recognition Fusion","volume":"78","author":"Abozaid","year":"2019","journal-title":"Multimed Tools Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Chen, G., Chenb, S., Fan, L., Du, X., Zhao, Z., Song, F., and Liu, Y. (2021, January 24\u201327). Who Is Real Bob? Adversarial Attacks on Speaker Recognition Systems. Proceedings of the 2021 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, S., Wu, H., Lee, H.-Y., and Meng, H. (2019, January 14\u201318). Adversarial Attacks on Spoofing Countermeasures of Automatic Speaker Verification. Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Sentosa, Singapore.","DOI":"10.1109\/ASRU46091.2019.9003763"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jiang, Z., Villalba, J., and Dehak, N. (2020, January 25). Black-Box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Examples. Proceedings of the Interspeech 2020, ISCA, Online.","DOI":"10.21437\/Interspeech.2020-2834"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Du, C., and Zhang, L. (2021). Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network. Remote Sens., 13.","DOI":"10.3390\/rs13214358"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"558","DOI":"10.3390\/make2040030","article-title":"Probabilistic Jacobian-Based Saliency Maps Attacks","volume":"2","author":"Combey","year":"2020","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Marcus Tan, Y.X., Iacovazzi, A., Homoliak, I., Elovici, Y., and Binder, A. (2019, January 14\u201319). Adversarial Attacks on Remote User Authentication Using Behavioural Mouse Dynamics. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.","DOI":"10.1109\/IJCNN.2019.8852414"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, E., Di Troia, F., and Stamp, M. (2021). Evaluating Deep Learning Models and Adversarial Attacks on Accelerometer-Based Gesture Authentication. arXiv.","DOI":"10.1007\/978-3-030-97087-1_10"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., and Song, D. (2021, October 13). Natural Adversarial Examples. Available online: https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Hendrycks_Natural_Adversarial_Examples_CVPR_2021_paper.html.","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Pestana, C., Liu, W., Glance, D., and Mian, A. (2021, January 5\u20139). Defense-Friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikola, HI, USA.","DOI":"10.1109\/WACV48630.2021.00060"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"10","DOI":"10.5334\/jors.238","article-title":"FluidFFT: Common API (C++ and Python) for Fast Fourier Transform HPC libraries","volume":"7","author":"Mohanan","year":"2019","journal-title":"J. Open Res. Softw."},{"key":"ref_25","unstructured":"Nicolae, M.-I., Sinn, M., Minh, T.N., Rawat, A., Wistuba, M., Zantedeschi, V., Molloy, J.M., and Edwards, B. (2021, November 29). Adversarial Robustness Toolbox v0.2.2. Available online: https:\/\/openreview.net\/forum?id=LjClBNOADBzB."},{"key":"ref_26","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2015). Explaining and Harnessing Adversarial Examples. arXiv, Available online: http:\/\/arxiv.org\/abs\/1412.6572."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Andriushchenko, M., Croce, F., Flammarion, N., and Hein, M. (2020). Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. arXiv, Available online: http:\/\/arxiv.org\/abs\/1912.00049.","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ross, A.S., and Doshi-Velez, F. (2017). Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients. arXiv, Available online: http:\/\/arxiv.org\/abs\/1711.09404.","DOI":"10.1609\/aaai.v32i1.11504"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ebrahimi, J., Rao, A., Lowd, D., and Dou, D. (2018). HotFlip: White-Box Adversarial Examples for Text Classification. arXiv, Available online: http:\/\/arxiv.org\/abs\/1712.06751.","DOI":"10.18653\/v1\/P18-2006"},{"key":"ref_30","unstructured":"Cha, S., Ko, N., Yoo, Y., and Moon, T. (2021). NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations. arXiv, Available online: http:\/\/arxiv.org\/abs\/2106.11644."},{"key":"ref_31","unstructured":"Papernot, N., McDaniel, P., and Goodfellow, I. (2016). Transferability in Machine Learning: From Phenomena to Black-Box Attacks Using Adversarial Samples. arXiv, Available online: http:\/\/arxiv.org\/abs\/1605.07277."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/2\/77\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T18:28:21Z","timestamp":1721932101000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/2\/77"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,5]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["info13020077"],"URL":"https:\/\/doi.org\/10.3390\/info13020077","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,5]]}}}