SUN’IY INTELLEKTGA ASOSLANGAN ZARARLI DASTURLARNI ANIQLASH USULLARI VA ALGORITMLARI ISHLAB CHIQISH
Keywords:
Sun’iy intellekt, zararli dasturlarni aniqlash, evristik aniqlash kiberxavfsizlik, Mashinali o‘qitish, chuqur o‘rganish, tahdidlarni aniqlash, anomaliyalarni aniqlash, kiber tahdidlar, zero-day tahdidlar.Abstract
Ushbu maqolada AI asosida yondashuvlarni kiberxavfsizlik himoyasini mustahkamlashda muhim vosita sifatida ta’kidlaydi. Maqola AI asosidagi zararli dasturlarni aniqlash tizimlarining an’anaviy usullarga nisbatan afzalliklarini ko‘rsatadi va yangi tahdidlarga qarshi kurashish uchun Mashinali o‘qitish algoritmlarini doimiy ravishda takomillashtirish zarurligini ta’kidlaydi.
Downloads
References
Check Point Research. (2023). AI Asosidagi kiberhujumlar statistikasi. Retrieved from https://www.checkpoint.com
CrowdStrike. (2023). 2023 Global Threat Report. Retrieved from https://www.crowdstrike.com
Proofpoint. (2022). Phishing hujumlarining AI tomonidan amalga oshirilishi bo‘yicha tadqiqot. Retrieved from https://www.proofpoint.com
Symantec. (2022). AI yordamida amalga oshirilgan ransomware hujumlari. Retrieved from https://www.broadcom.com/company/newsroom/press-releases
Google Rapid Response (GRR) loyihasi. Retrieved from https://github.com/google/grr
REMnux – Zararli dasturlarni tahlil qilish muhitlari. Retrieved from https://remnux.org
Cuckoo Sandbox – Ochiq kodli zararli dasturlarni tahlil qilish vositasi. Retrieved from https://cuckoosandbox.org
VirusTotal – Zararli dasturlarni aniqlash xizmati. Retrieved from https://www.virustotal.com
Wireshark – Tarmoq trafigini tahlil qilish vositasi. Retrieved from https://www.wireshark.org
Sanjay Sharma, et al. (2021). Opcode paydo bo‘lish chastotasiga asoslangan zararli dasturlarni aniqlash usuli. IEEE Transactions on Information Forensics and Security, 16, 2873-2885.
Niharika Sharma. (2020). Zararli dasturlarni aniqlash texnikalarini Mashinali o‘qitish orqali baholash. Journal of Cybersecurity Research, 12(4), 134-150.
