Araştırma Makalesi
BibTex RIS Kaynak Göster

Karanlık Web İstihbaratı ve Makine Öğrenmesi Tabanlı Anomali Tespiti ile Otomatik Tehdit Algılama ve Güvenlik Duvarı Kural Yönetimi

Yıl 2025, Cilt: 8 Sayı: 2, 49 - 69, 24.12.2025
https://izlik.org/JA93FD68SR

Öz

Bu makale, Karanlık Web tehdit istihbaratını gerçek zamanlı güvenlik duvarı kural yönetimi ve makine öğrenmesi tabanlı ağ anomali tespiti ile otonom olarak entegre eden devrim niteliğinde bir siber güvenlik çerçevesi sunmaktadır. Önerilen sistem, Karanlık Web üzerindeki iletişimlerden gelişmiş tehdit istihbaratı çıkarmak için Büyük Dil Modelleri’ni (LLM'ler) kullanmakta, Check Point güvenlik duvarı altyapıları ile sorunsuz bir şekilde entegre olarak otomatik kural doğrulama ve üretimi gerçekleştirmekte, ayrıca FortiGate ağ trafiğini analiz etmek için gelişmiş makine öğrenmesi algoritmalarını uygulamaktadır.

Bu yenilikçi hibrit yaklaşım, geleneksel imza tabanlı tespit sistemlerine kıyasla %94,7 tehdit tespit doğruluğu ve %68 oranında yanlış pozitiflerde azalma ile dikkate değer performans iyileştirmeleri sergilemiştir. Çerçeve, Karanlık Web iletişimlerinin doğal dil işleme süreçlerinde Google’ın Gemini LLM’ini kullanmakta, tespit edilen tehditleri mevcut güvenlik duvarı kural tabanlarıyla otomatik olarak çapraz referanslamakta ve gerçek zamanlı olarak uyarlanabilir güvenlik politikaları üretmektedir.

Sistem, temel ağ trafiği desenlerini oluşturmak için K-Ortalamalar (K-Means) kümeleme yöntemini ve zamansal dizi analizi ile sıfırıncı gün tehditlerinin tespiti için Uzun Kısa Süreli Bellek (LSTM) sinir ağlarını kullanan çok katmanlı gelişmiş bir anomali tespit mekanizması uygulamaktadır.

Kapsamlı performans değerlendirmeleri, sistemin saniyede 15.000’den fazla ağ akışını işleyebildiğini ve kritik tehdit uyarıları için 100 milisaniyenin altında yanıt sürelerini koruduğunu göstermektedir. Altı aylık değerlendirme süresince sistem, 342 benzersiz güvenlik tehdidini başarıyla tespit etmiş; bunların 127’si daha önce bilinmeyen saldırı desenleri, 89’u sıfırıncı gün açık istismar girişimi ve 126’sı gelişmiş sürekli tehdit (APT) göstergeleridir.

Otomatik güvenlik duvarı kural üretimi ile üretim ortamlarında %92,3 etkinlik oranına sahip 1.847 güvenlik politikası oluşturulmuştur. Sistemin modüler mimarisi, mevcut kurumsal güvenlik altyapılarıyla sorunsuz entegrasyonu mümkün kılarken; artırılmış tehdit görünürlüğü, proaktif tehdit önleme ve heterojen ağ ortamlarında tamamen otomatik güvenlik yanıt koordinasyonu sağlamaktadır.

Kaynakça

  • MITRE Corporation, “MITRE ATT&CK® Framework,” tech. rep., MITRE Corporation, 2024.
  • NIST, “Cybersecurity Framework 2.0,” Tech. Rep. NIST CSF 2.0, National Institute of Standards and Technology, 2023.
  • IBM Security, “Cost of a Data Breach Report 2024,” tech. rep., IBM Corporation, 2024.
  • Schafer, M., Fuchs, M., Strohmeier, M., Engel, M., Liechti, M., Lenders, V. , “BlackWidow: Monitoring the Dark Web for Cyber Security Information,” 2023.
  • D. Bringhenti, G. Marchetto, R. Sisto, F. Valenza, and J. Yusupov, “Automatic Allocation and Configuration of Packet Filters in Virtual Networks,” IEEE Transactions on Dependable and Secure Computing, vol. 20, no. 2, pp. 1559–1572, 2023.
  • J. Cannady and J. Harrell, “A comparative analysis of current intrusion detection technologies,” in Proceedings of the Fourth Technology for Information Security Conference, vol. 96, May 1996.
  • G. Gonza´lez-Granadillo, S. Gonza´lez-Zarzosa, and R. Diaz, “Security information and event management (SIEM): analysis, trends, and usage in critical infrastructures,” Sensors, vol. 21, no. 14, p. 4759, 2021.
  • J. Wang, L. Yang, J. Wu, and J. H. Abawajy, “Clustering analysis for malicious network traffic,” in 2017 IEEE International Conference on Communications (ICC), pp. 1–6, IEEE, May 2017.
  • P. V. Sai Charan, T. Gireesh Kumar, and P. Mohan Anand, “Advance persistent threat detection using long short term memory (LSTM) neural networks,” in International Conference on Emerging Technologies in Computer Engineering, (Singapore), pp. 45–54, Springer Singapore, February 2019.
  • H. Sayadi, N. Patel, A. Sasan, S. Rafatirad, and H. Homayoun, “Ensem-ble learning for effective run-time hardware-based malware detection: A comprehensive analysis and classification,” in Proceedings of the 55th annual design automation conference, pp. 1–6, June 2018.
  • A. Dalvi, G. Patil, and S. G. Bhirud, “Dark Web Marketplace Monitoring-The Emerging Business Trend of Cybersecurity,” in 2022 In-ternational Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), pp. 1–6, IEEE, October 2022.
  • S. Al-Thani, “Content Sentiment Analysis on the Dark Web,” Master’s thesis, Hamad Bin Khalifa University (Qatar), 2022.
  • F. N. Motlagh, M. Hajizadeh, M. Majd, P. Najafi, F. Cheng, and C. Meinel, “Large language models in cybersecurity: State-of-the-art,” arXiv preprint arXiv:2402.00891, 2024.
  • S. R. Gudimetla, “Beyond the barrier: Advanced strategies for firewall implementation and management,” NeuroQuantology, vol. 13, no. 4,pp. 558–565, 2015. Q. A. Al-Haijaa and A. Ishtaiwia, “Machine learning based model to identify firewall decisions to improve cyber-defense,” International Journal of Advanced Science and Engineering Information Technology, vol. 11, no. 4, pp. 1688–1695, 2021.
  • D. Bringhenti, L. Seno, and F. Valenza, “An optimized approach for assisted firewall anomaly resolution,” IEEE Access, vol. 11, pp. 119693–119710, 2023.
  • H. Y. Kwon, T. Kim, and M. K. Lee, “Advanced intrusion detec-tion combining signature-based and behavior-based detection methods,” Electronics, vol. 11, no. 6, p. 867, 2022.
  • D. Chatziamanetoglou and K. Rantos, “Blockchain-Based Cyber Threat Intelligence Sharing Using Proof-of-Quality Consensus,” Security and Communication Networks, vol. 2023, p. 3303122, 2023.
  • L. Chen and M. Wang, “Advanced Clustering Techniques for Network Anomaly Detection in Cloud Environments,” Journal of Network and Computer Applications, vol. 201, p. 103578, 2024.
  • R. Smith, K. Anderson, and J. Lee, “Deep Learning Approaches for Real-Time Network Traffic Classification and Analysis,” IEEE Network, vol. 37, no. 2, pp. 45–52, 2023.

A Machine Learning-Driven System for Automated Threat Detection and Firewall Rule Management Using Dark Web Intelligence

Yıl 2025, Cilt: 8 Sayı: 2, 49 - 69, 24.12.2025
https://izlik.org/JA93FD68SR

Öz

This paper presents a revolutionary cybersecurity framework that autonomously integrates Dark Web threat intelligence with real-time firewall rule management and machine learning-driven network anomaly detection. The proposed system employs Large Language Models (LLMs) for sophisticated threat intelligence extraction from Dark Web communications, seamlessly integrates with Check Point firewall infrastructures for automated rule validation and generation, and utilizes advanced machine learning algorithms for FortiGate network traffic analysis.

Our innovative hybrid approach demonstrates significant performance improvements, achieving 94.7% threat detection accuracy alongside a 68% reduction in false positive rates compared to conventional signature-based detection systems. The framework leverages Google’s Gemini LLM for natural language processing of Dark Web content, automatically cross-references identified threats against existing firewall rule-bases, and generates adaptive security policies in real time.

The system implements a multi-layer anomaly detection mechanism using K-Means clustering to establish baseline traffic patterns, and Long Short-Term Memory (LSTM) neural networks for temporal sequence analysis and zero-day threat identification. Comprehensive performance evaluations reveal the system's ability to process over 15,000 network flows per second while maintaining sub-100 millisecond response times for critical threat alerts.

Over a 6-month evaluation period, the framework successfully identified 342 unique security threats, including 127 previously unknown attack patterns, 89 zero-day exploit attempts, and 126 advanced persistent threat (APT) indicators. The automated firewall rule generation engine produced 1,847 security policies with 92.3% effectiveness in production environments.

The system’s modular architecture enables seamless integration with existing enterprise security infrastructures, delivering enhanced threat visibility, proactive threat mitigation, and fully automated security response coordination across heterogeneous network environments.

Kaynakça

  • MITRE Corporation, “MITRE ATT&CK® Framework,” tech. rep., MITRE Corporation, 2024.
  • NIST, “Cybersecurity Framework 2.0,” Tech. Rep. NIST CSF 2.0, National Institute of Standards and Technology, 2023.
  • IBM Security, “Cost of a Data Breach Report 2024,” tech. rep., IBM Corporation, 2024.
  • Schafer, M., Fuchs, M., Strohmeier, M., Engel, M., Liechti, M., Lenders, V. , “BlackWidow: Monitoring the Dark Web for Cyber Security Information,” 2023.
  • D. Bringhenti, G. Marchetto, R. Sisto, F. Valenza, and J. Yusupov, “Automatic Allocation and Configuration of Packet Filters in Virtual Networks,” IEEE Transactions on Dependable and Secure Computing, vol. 20, no. 2, pp. 1559–1572, 2023.
  • J. Cannady and J. Harrell, “A comparative analysis of current intrusion detection technologies,” in Proceedings of the Fourth Technology for Information Security Conference, vol. 96, May 1996.
  • G. Gonza´lez-Granadillo, S. Gonza´lez-Zarzosa, and R. Diaz, “Security information and event management (SIEM): analysis, trends, and usage in critical infrastructures,” Sensors, vol. 21, no. 14, p. 4759, 2021.
  • J. Wang, L. Yang, J. Wu, and J. H. Abawajy, “Clustering analysis for malicious network traffic,” in 2017 IEEE International Conference on Communications (ICC), pp. 1–6, IEEE, May 2017.
  • P. V. Sai Charan, T. Gireesh Kumar, and P. Mohan Anand, “Advance persistent threat detection using long short term memory (LSTM) neural networks,” in International Conference on Emerging Technologies in Computer Engineering, (Singapore), pp. 45–54, Springer Singapore, February 2019.
  • H. Sayadi, N. Patel, A. Sasan, S. Rafatirad, and H. Homayoun, “Ensem-ble learning for effective run-time hardware-based malware detection: A comprehensive analysis and classification,” in Proceedings of the 55th annual design automation conference, pp. 1–6, June 2018.
  • A. Dalvi, G. Patil, and S. G. Bhirud, “Dark Web Marketplace Monitoring-The Emerging Business Trend of Cybersecurity,” in 2022 In-ternational Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), pp. 1–6, IEEE, October 2022.
  • S. Al-Thani, “Content Sentiment Analysis on the Dark Web,” Master’s thesis, Hamad Bin Khalifa University (Qatar), 2022.
  • F. N. Motlagh, M. Hajizadeh, M. Majd, P. Najafi, F. Cheng, and C. Meinel, “Large language models in cybersecurity: State-of-the-art,” arXiv preprint arXiv:2402.00891, 2024.
  • S. R. Gudimetla, “Beyond the barrier: Advanced strategies for firewall implementation and management,” NeuroQuantology, vol. 13, no. 4,pp. 558–565, 2015. Q. A. Al-Haijaa and A. Ishtaiwia, “Machine learning based model to identify firewall decisions to improve cyber-defense,” International Journal of Advanced Science and Engineering Information Technology, vol. 11, no. 4, pp. 1688–1695, 2021.
  • D. Bringhenti, L. Seno, and F. Valenza, “An optimized approach for assisted firewall anomaly resolution,” IEEE Access, vol. 11, pp. 119693–119710, 2023.
  • H. Y. Kwon, T. Kim, and M. K. Lee, “Advanced intrusion detec-tion combining signature-based and behavior-based detection methods,” Electronics, vol. 11, no. 6, p. 867, 2022.
  • D. Chatziamanetoglou and K. Rantos, “Blockchain-Based Cyber Threat Intelligence Sharing Using Proof-of-Quality Consensus,” Security and Communication Networks, vol. 2023, p. 3303122, 2023.
  • L. Chen and M. Wang, “Advanced Clustering Techniques for Network Anomaly Detection in Cloud Environments,” Journal of Network and Computer Applications, vol. 201, p. 103578, 2024.
  • R. Smith, K. Anderson, and J. Lee, “Deep Learning Approaches for Real-Time Network Traffic Classification and Analysis,” IEEE Network, vol. 37, no. 2, pp. 45–52, 2023.
Toplam 19 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Makine Öğrenme (Diğer)
Bölüm Araştırma Makalesi
Yazarlar

Yasin Çarkçı 0009-0006-9181-6380

Alperen Sayar 0000-0001-6089-2547

Seyit Ertuğrul 0000-0003-0828-7336

Gorkem Demircan 0009-0000-9302-7111

Boran Ertuğrul 0009-0001-7614-484X

Gönderilme Tarihi 4 Ağustos 2025
Kabul Tarihi 7 Kasım 2025
Yayımlanma Tarihi 24 Aralık 2025
IZ https://izlik.org/JA93FD68SR
Yayımlandığı Sayı Yıl 2025 Cilt: 8 Sayı: 2

Kaynak Göster

APA Çarkçı, Y., Sayar, A., Ertuğrul, S., Demircan, G., & Ertuğrul, B. (2025). A Machine Learning-Driven System for Automated Threat Detection and Firewall Rule Management Using Dark Web Intelligence. Veri Bilimi, 8(2), 49-69. https://izlik.org/JA93FD68SR


 


Dergimizin Tarandığı Dizinler (İndeksler)
 

 

 

Academic Resource Index

logo.png

Google Scholar

scholar_logo_64dp.png

ASOS Index

asos-index.png

Rooting Index

logo.png

Directory of Research Journals Indexing
 DRJI_Logo.jpg