Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben
Programming and Computer Software
Erschienen in: Programming and Computer Software 2/2023

01.12.2023

Analysis of Vulnerabilities of Neural Network Image Recognition Technologies

verfasst von: A. V. Trusov, E. E. Limonova, V. V. Arlazarov, A. A. Zatsarinnyy

Erschienen in: Programming and Computer Software | Sonderheft 2/2023

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The problem of vulnerability of artificial intelligence technologies based on neural networks is considered. It is shown that the use of neural networks generates a lot of vulnerabilities. Examples of such vulnerabilities are demonstrated, such as incorrect classification of images containing adversarial noise or patches, failure of recognition systems in the presence of special patterns in the image, including those applied to objects in the real world, training data poisoning, etc. Based on the analysis, the need to improve the security of artificial intelligence technologies is shown, and some considerations that contribute to this improvement are discussed.
Vorheriger Artikel Layer-by-Layer Knowledge Distillation for Training Simplified Bipolar Morphological Neural Networks
Nächster Artikel Improving Fuzzing Using Input Data Offsets Comparison Information

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Literatur
1.
Ye, M. et al., Deep learning for person re-identification: A survey and outlook, IEEE Trans. Pattern Anal. Mach. Intell., 2021, vol. 44, no. 6, pp. 2872–2893.CrossRef
2.
Arlazarov, V.V., Andreeva, E.I., Bulatov, K.B., Nikolaev, D.P., Petrova, O.O., Savelev B.I., and Slavin, O.A., Document image analysis and recognition: A survey, Komput. Optika, 2022, vol. 46, no. 4, pp. 567–589.ADS
3.
Yang, B. et al., Edge intelligence for autonomous driving in 6G wireless system: Design challenges and solutions, IEEE Wireless Commun., 2021, vol. 28, no. 2, pp. 40–47.CrossRef
4.
Gu, T., Dolan-Gavitt, B., and Garg, S., Badnets: Identifying vulnerabilities in the machine learning model supply chain, arXiv:1708.06733, 2017.
5.
Fredrikson, M., Jha, S., and Ristenpart, T., Model inversion attacks that exploit confidence information and basic countermeasures, Proc. of the 22nd ACM SIGSAC Conference on Computer and Communications Security, 2015, pp. 1322–1333.
6.
Szegedy C. et al., Intriguing properties of neural networks, arXiv:1312.6199, 2013.
7.
Brown, T.B. et al., Adversarial patch, arXiv:1712.09665, 2017.
8.
Lin, C.S. et al., Real-world adversarial examples via makeup, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022, pp. 2854–2858.
9.
Hu, S. et al. Protecting facial privacy: Generating adversarial identity masks via style-robust makeup transfer, Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 15014–15023.
10.
Zolfi, A. et al., Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Models, Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Cham: Springer Nature Switzerland, 2022, pp. 304–320.
11.
Zhou, Z. et al., Invisible mask: Practical attacks on face recognition with infrared, arXiv:1803.04683, 2018.
12.
Wu, Z., Lim, S.N., Davis, L.S., and Goldstein, T., Making an invisibility cloak: Real world adversarial attacks on object detectors, Proc. of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, 2020, Part 4, pp. 1–17.
13.
Thys, S., Van Ranst, W., and Goedemé, T., Fooling automated surveillance cameras: adversarial patches to attack person detection, Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. https://openaccess.thecvf.com/content_CVPRW_2019/html/CV-COPS/Thys_Fooling_Automated_ Surveillance_Cameras_Adversarial_Patches_to_Attack_Person_Detection_CVPRW_2019_paper.html.
14.
Chen, J. et al., Diffusion Models for Imperceptible and Transferable Adversarial Attack, arXiv:2305.08192, 2023.
15.
Hong, S. et al., Security analysis of deep neural networks operating in the presence of cache side-channel attacks, arXiv:1810.03487, 2018.
16.
Oh, S.J., Schiele, B., and Fritz, M., Towards reverse-engineering black-box neural networks, in Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 2019 pp. 121–144.
17.
Chmielewski, Ł., and Weissbart, L., On reverse engineering neural network implementation on GPU, Proc. of the Applied Cryptography and Network Security Workshops: ACNS 2021 Satellite Workshops, AIBlock, AIHWS, AIoTS, CIMSS, Cloud S&P, SCI, SecMT, and SiMLA, Kamakura, Japan, 2021, Springer, 2021, pp. 96–113.
18.
Goldblum, M. et al., Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses, IEEE Trans. Pattern Anal. Mach, Intell., 2022, vol. 45, no. 2, pp. 1563–1580.CrossRef
19.
Shafahi, A. et al., Poison frogs! Targeted clean-label poisoning attacks on neural networks, Advances in neural information processing systems, 2018, vol. 31.
20.
Wang, Y. et al. Sapag: A self-adaptive privacy attack from gradients, arXiv:2009.06228, 2020.
21.
Warr, K., Strengthening Deep Neural Networks: Making AI Less Susceptible to Adversarial Trickery, O’Reilly, 2019.
22.
Akhtar, N. and Mian, A., Threat of adversarial attacks on deep learning in computer vision: A survey, IEEE Access, vol. 2018, no. 6, pp. 14410–14430
23.
Machado, G.R., Silva, E., and Goldschmidt, R.R., Adversarial machine learning in image classification: A survey toward the defender’s perspective, ACM Comput. Surveys (CSUR), 2021, vol. 55, no. 1, pp. 1–38.CrossRef
24.
Long, T. et al., A survey on adversarial attacks in computer vision: Taxonomy, visualization and future directions, Comput. & Security, 2022, p. 102847.
25.
Ren, K. et al., Adversarial attacks and defenses in deep learning, Engineering, 2020, vol. 6, no. 3, pp. 346–360.CrossRef
26.
Zhang, X. et al., Imperceptible black-box waveform-level adversarial attack towards automatic speaker recognition, Complex & Intell. Syst., 2023, vo. 9, no. 1, pp. 65–79.CrossRef
27.
Kwon, H. and Lee, S., Ensemble transfer attack targeting text classification systems, Comput. & Security, 2022, vol. 117, p. 102695.
28.
Mo, K. et al. Attacking deep reinforcement learning with decoupled adversarial policy, IEEE Trans. Dependable Secure Comput., 2022, vol. 20, no. 1, pp. 758–768.CrossRef
29.
Zhou, X. et al., Hierarchical adversarial attacks against graph-neural-network-based IoT network intrusion detection system, IEEE IoT J., 2021, vol. 9, no. 12, pp. 9310–9319.
30.
Kumar, R.S.S. et al., Adversarial machine learning-industry perspectives, IEEE Security and Privacy Workshops (SPW), IEEE, 2020, pp. 69–75.
31.
Paleyes, A., Urma, R.G., and Lawrence, N.D., Challenges in deploying machine learning: A survey of case studies, ACM Comput. Surveys, 2022, vol. 55, no. 6, pp. 1–29.CrossRef
32.
Ala-Pietilä, P. et al., The Assessment List for Trustworthy Artificial Intelligence (ALTAI), European Commission, 2020.
33.
Musser, M. et al., Adversarial machine learning and cybersecurity: Risks, challenges, and legal implications, arXiv:2305.14553, 2023.
34.
Facial recognition’s latest foe: Italian knitwear. https://​therecord.​media/​facial-recognitions-latest-foe-italian-knitwear. Accessed July 20, 2023.
35.
How we fight content copying, or the first adversarial attack in production. https://​habr.​com/​ru/​companies/​avito/​articles/​452142. Accessed July 20, 2023.
36.
Povolny, S. and Trivedi, S., Model hacking ADAS to pave safer roads for autonomous vehicles. https://​www.​mcafee.​com/​blogs/​other-blogs/​mcafee-labs/​model-hacking-adas-to-pave-safer-roads-for-autonomous-vehicles/​.​ Accessed July 20, 2023.
Metadaten
Titel
Analysis of Vulnerabilities of Neural Network Image Recognition Technologies
verfasst von
A. V. Trusov
E. E. Limonova
V. V. Arlazarov
A. A. Zatsarinnyy
Publikationsdatum
01.12.2023
Verlag
Pleiades Publishing
Erschienen in
Programming and Computer Software / Ausgabe Sonderheft 2/2023
Print ISSN: 0361-7688
Elektronische ISSN: 1608-3261
DOI
https://doi.org/10.1134/S0361768823100079

Weitere Artikel der Sonderheft 2/2023

Programming and Computer Software 2/2023 Zur Ausgabe

OriginalPaper

White Balance Correction for Detecting Holograms in Color Images of Black-and-White Photographs

OriginalPaper

Layer-by-Layer Knowledge Distillation for Training Simplified Bipolar Morphological Neural Networks

OriginalPaper

Improving Fuzzing Using Input Data Offsets Comparison Information

OriginalPaper

Optimal Placement of Base Stations in Integrated Design of Wireless Networks

OriginalPaper

Analysis of Traces on Discharged Bullets by the Congruent Matching Profile Segments Method and k-Nearest Neighbors

OriginalPaper

Knowledge Base Generation Based on Fuzzy Clustering

Premium Partner

    Bildnachweise