FAYL METAMA’LUMOTLARINI HIMOYALASHDA SUN’IY INTELLEKT ASOSIDA TAHDIDLARNI ANIQLASH VA JAVOB QAYTARISH ALGORITMLARI

Sodiqova D. J.


Annotatsiya

Ushbu maqolada raqamli hujjatlar tarkibidagi metama’lumotlarni himoyalash bo‘yicha sun’iy intellekt asosidagi tahdidlarni aniqlash va avtomatik javob qaytarish modeli ishlab chiqildi. Metama’lumotlar — muallif, yaratilish va tahrir vaqti, GPS koordinatalar, qurilma identifikatori, versiya tarixi kabi texnik atributlar — ko‘pincha foydalanuvchi tomonidan nazorat qilinmaydi, biroq ular sezilarli xavfsizlik xatarlari manbai hisoblanadi. Tadqiqotda Autoencoder, LSTM, Isolation Forest kabi AI modellaridan foydalanilib, metadata anomaliyalarining yuqori aniqlikda aniqlanishi ta’minlandi. Shuningdek, AES-GCM, RSA-OAEP va SHA-3 algoritmlariga asoslangan selektiv kriptografik himoya modeli ishlab chiqilib, metadata qatlamining maxfiyligi va yaxlitligi oshirildi. Tarmoq darajasida TLS 1.3, DPI va IDS/IPS texnologiyalari yordamida tranzit jarayonidagi metadata sizishining oldi olindi. Natijalar taklif etilgan model raqamli hujjatlar xavfsizligi uchun kompleks, moslashuvchan va samarali yechim ekanligini ko‘rsatdi.


Adabiyotlar

  1. Kesan, J. P., & Hayes, C. E. (2019). Metadata, privacy, and security in digital documents: Risks and countermeasures. Computer Law & Security Review, 35(6), 105342.
  2. Lillis, D., Becker, B., O’Sullivan, T., & Scanlon, M. (2016). Current challenges and future research areas for digital forensics: A survey. arXiv preprint arXiv:1604.03850.
  3. Haraty, R. A., & Yamout, A. (2012). A survey of hidden data detection in digital images. Digital Investigation, 8(1), 34–43.
  4. Chen, Y., Wang, S., & Yu, Z. (2020). Deep learning-based anomaly detection in cybersecurity: A review. IEEE Access, 8, 205383–205402.
  5. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
  6. Kim, Y., Kim, S., & Choi, J. (2021). Metadata-based cyber threat detection using machine learning. Journal of Information Security and Applications, 59, 102827.
  7. Stallings, W. (2017). Cryptography and Network Security: Principles and Practice. Pearson Education.
  8. Dworkin, M. (2016). NIST SP 800-38D: Recommendation for Block Cipher Modes of Operation: Galois/Counter Mode (GCM). Gaithersburg: National Institute of Standards and Technology.
  9. NIST (2015). Secure Hash Standard (SHS), FIPS PUB 180-4. National Institute of Standards and Technology.
  10. Krawczyk, H., Bellare, M., & Canetti, R. (1997). HMAC: Keyed-hashing for message authentication. RFC 2104, Internet Engineering Task Force.
  11. Rescorla, E. (2018). The Transport Layer Security (TLS) Protocol Version 1.3. RFC 8446.
  12. Hindy, H., Brosset, D., Bayne, E. et al. (2020). A taxonomy and survey of intrusion detection system design techniques, network threats and datasets. Artificial Intelligence Review, 53, 435–487.
  13. Cao, J., Zhang, H., & Feng, W. (2018). PDF metadata security vulnerabilities: Detection and prevention. Information Sciences, 453, 186–199.
  14. Peña, A., & Choo, K.-K. R. (2022). Intelligent models for cyber threat detection: Deep learning and big data perspectives. Future Generation Computer Systems, 129, 138–152.
  15. Sarker, I. H. (2021). Machine learning-based cybersecurity: Principles, challenges and future directions. Internet of Things, 14, 100393.
  16. Garfinkel, S. L. (2013). Digital forensics: An integrated approach. Communications of the ACM, 56(11), 64–73.
  17. Zhang, J., Lin, Z., & Wang, J. (2021). Multi-layer metadata protection framework for secure document management. IEEE Transactions on Information Forensics and Security, 16, 2357–2371.
  18. Bishop, M. (2005). Introduction to Computer Security. Addison-Wesley.
  19. Al-Qershi, O. M., & Othman, M. (2020). Cybersecurity threats and defense: AI-based solutions. Computer Networks, 180, 107390.
  20. Grose, J., Lakhani, K., & Turner, D. (2021). Machine learning in cyber forensics: Applications and challenges. Forensic Science International: Digital Investigation, 38, 301134.
  21. O‘zbekiston Respublikasi Milliy Standarti — O‘zMSt 270:2024. Axborot xavfsizligi. Kriptografik himoya. O‘zbekiston Texnik jihatdan tartibga solish agentligi, 2024.
  22. European Union Agency for Cybersecurity (ENISA) (2022). Metadata Security and Privacy Guidelines. Luxemburg: Publications Office of the EU.
  23. Ross, R., Pillitteri, V., & Dempsey, K. (2020). NIST SP 800-53: Security and Privacy Controls for Information Systems. National Institute of Standards and Technology.
  24. Shah, S., & Mehta, S. (2019). AI-driven document forensics and metadata integrity verification. Applied Sciences, 9(16), 3290.
  25. Zhang, K., Liang, X., & Wang, R. (2019). Deep neural network-based anomaly detection in digital document structures. Pattern Recognition, 91, 99–112.