Research Article
BibTex RIS Cite

The Development ff Artıfıcıal Intellıgence in IPS Systems in The Last Five Years

Year 2022, Volume: IDAP-2022 : International Artificial Intelligence and Data Processing Symposium , 211 - 218, 10.10.2022
https://doi.org/10.53070/bbd.1172803

Abstract

Today, IPS (Intrusion Prevention Systems), which is one of the cornerstones of cyber security, has been getting rid of the traditional human-controlled defense strategy since 2017 and has been implementing a new defense strategy with artificial intelligence and machine learning integration, also known as NGIPS (Next Generation Intrusion Prevention Systems). These new IPS solutions integrated with artificial intelligence have been used in attack prevention with different algorithms and techniques over the years. In this study, information about these systems integrated into artificial intelligence is given and its development in the last five years is examined in general IPS solutions and fortinet IPS Fortinet. Defense with this artificial intelligence in IPS solutions has developed in direct proportion as a result of attacks made with artificial intelligence. Machine learning in IPS solutions uses three basic techniques. These are data collection, feature selection, and model building. Finally, artificial intelligence algorithms evaluate the data classified by the modeling method and intervene positively or negatively. Traditional methods, that is, pre-artificial intelligence methods were insufficient in these perceptions. The existence and development of artificial intelligence in IPS systems have become mandatory due to the developing cyber attacks and the fact that new vulnerabilities discovered day by day are beyond human limits.
It is evaluated that this study will create awareness about the importance of artificial intelligence development in IPS in cyber defense.

References

  • Borman, K. (2019). Datacenter ıntrusion prevention system test report. texas: NSS laps.
  • Buduma, N., & Locascio, N. (2017). Fundamentals of deep learning: designing next-generation. O'Reilly media.
  • Costa, C. F. (2021). Artificial ıntelligence & cybersecurity: european union panorama. societa ıtaliana per ı'l organizzazione ınternazionale. pedralva.
  • Cyberedge. (2022). Cyberthreat defense report. NewYork: cyber edge research labs.
  • Das, S., & Nene, M. J. (2017). A survey on types of machine learning techniques in ıntrusion prevention systems. ıeee wispnet 2017. ıeee.
  • ENISA. (2018). Cybersecurity culture guidelines: behavioral aspects of cybersecurity. enısa. doi:doı: 10.2824/324042
  • EPRI. (2020). Cyber security road map. california: eprı.
  • Fortinet. (2022). Investor presentation. amsterdam: fortinet labs.
  • Marinos, L., Lourenco, M. B. (2020). Main incidents in the eu and worldwide enısa threat landscape. enısa.
  • Micro, T. (2017). Machine learning and ngıps. ABD
  • Patel, A., Qassim, Q., & Wills, C. (2010). Ids and ıps research. ınformation and computer security.
  • Qu, S., Li, X., Szurley, J., Kolter, J. Z., & Metze, F. (2019). Adversarial music: real-world audio adversary against wake-word detection system. 2019. Vancouver: neurıps.
  • Scarfone, K., & Mell, P. (2007). Guide to ıntrusion detection and prevention system. gaithersburg: nıst.
  • Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017). Membership ınference attacks against machine learning models. güvenlik ve gizlilik sempozyumu (s. 3-18). ıeee.
  • Tolido, R., Frank, A., Delabarre, L., & Cherian, S. (2020). Reinventing cybersecurity with artificial intelligence: the new frontier in digital security. amsterdam: capgemini researchınstitute.
  • Aslan, F. (2022, Nisan 14). iskulubu. https://iskulubu.com/manset/yapay-zekanin-en-onemli-5-avantaji-ve-dezavantaji/ Cimpanu, C. (2020, Ekim 17).
  • https://www.zdnet.com/article/first-death-reported-following-a-ransomware-attack-on-a-german-hospital/iisbf gelisim haber. (2021).
  • https://iisbf.gelisim.edu.tr/bolum/isletme-37/haber/stanford-universitesi-2021-yili yapay-zeka-raporu-yayimlandi McElfresh, M. (2016).https://theconversation.com/cyberattack-on-ukraine-grid-heres-how-it-worked-and-perhaps-why-it-was-done-52802
  • Voss RF, Clarke J. (1986) Algorithmic Musical Composition, Silver Burdett Press, London.
  • Zabierowski W, Napieralski A (2003) Chords classification in tonal music. Journal of Environment Studies 10(5): 50-53.
  • Abiewskiro A, Moplskiiera Z. (2008) The Problem Of Grammar Choice For Verification. TCSET of the International Conference, House of Lviv Polytechnic National University, pp.19-23.
  • Healthwise Knowledgebase (1998) US Pharmacopeia, Rockville. http://www.healthwise.org. Accessed 21 Sept 1998

IPS Sistemlerde Yapay Zekânın Son Beş Yıldaki Gelişimi

Year 2022, Volume: IDAP-2022 : International Artificial Intelligence and Data Processing Symposium , 211 - 218, 10.10.2022
https://doi.org/10.53070/bbd.1172803

Abstract

Günümüzde siber güvenliğin temel taşlarından olan IPS (Saldırı Önleme Sistemleri) 2017 yılından günümüze kadar geleneksel insan kontrollü savunma stratejisinden sıyrılıp, NGIPS (Yeni Nesil Saldırı Önleme Sistemleri) olarak da bilinen yapay zekâ ve makine öğrenimi entegrasyonlu yeni bir savunma stratejisine dönüşmüştür. Yapay zekaya entegre bu yeni IPS çözümleri yıllar içerisinde farklı algoritmalar ve teknikler ile saldırı önlemede kullanılmıştır. Bu çalışmada yapay zekaya entegre sistemler hakkında bilgi verilmiş ve son beş yıl içerisindeki gelişimi IPS çözümleri genelinde ve Fortinet IPS çözümü özelinde incelenmiştir. IPS çözümlerindeki bu yapay zekâ ile savunma, yine yapay zekâ ile yapılan saldırılar neticesinde doğru orantılı olarak gelişmiştir. IPS çözümlerinde makine öğrenimi üç temel teknikte kullanır. Bunlar, veri toplama, özellik seçimi ve model oluşturmadır. Model oluşturma yöntemi ile sınıflandırılan veriler yapay zekâ algoritmaları ile olumlu ya da olumsuz olarak değerlendirilip müdahale edilir. Geleneksel yöntemler yani yapay zekâ öncesi yöntemler bu algılamalarda yetersiz kalmıştır. Gelişen siber saldırılar ve her geçen gün keşfedilen yeni açıklıkların insan sınırlarının üzerinde olması sebebi ile IPS sistemlerde yapay zekânın var olması ve geliştirilmesi zorunlu hale gelmiştir.
Bu çalışmanın IPS’lerde yapay zekâ gelişiminin, siber savunmadaki önemi ile ilgili farkındalık yaratacağı değerlendirilmektedir.

References

  • Borman, K. (2019). Datacenter ıntrusion prevention system test report. texas: NSS laps.
  • Buduma, N., & Locascio, N. (2017). Fundamentals of deep learning: designing next-generation. O'Reilly media.
  • Costa, C. F. (2021). Artificial ıntelligence & cybersecurity: european union panorama. societa ıtaliana per ı'l organizzazione ınternazionale. pedralva.
  • Cyberedge. (2022). Cyberthreat defense report. NewYork: cyber edge research labs.
  • Das, S., & Nene, M. J. (2017). A survey on types of machine learning techniques in ıntrusion prevention systems. ıeee wispnet 2017. ıeee.
  • ENISA. (2018). Cybersecurity culture guidelines: behavioral aspects of cybersecurity. enısa. doi:doı: 10.2824/324042
  • EPRI. (2020). Cyber security road map. california: eprı.
  • Fortinet. (2022). Investor presentation. amsterdam: fortinet labs.
  • Marinos, L., Lourenco, M. B. (2020). Main incidents in the eu and worldwide enısa threat landscape. enısa.
  • Micro, T. (2017). Machine learning and ngıps. ABD
  • Patel, A., Qassim, Q., & Wills, C. (2010). Ids and ıps research. ınformation and computer security.
  • Qu, S., Li, X., Szurley, J., Kolter, J. Z., & Metze, F. (2019). Adversarial music: real-world audio adversary against wake-word detection system. 2019. Vancouver: neurıps.
  • Scarfone, K., & Mell, P. (2007). Guide to ıntrusion detection and prevention system. gaithersburg: nıst.
  • Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017). Membership ınference attacks against machine learning models. güvenlik ve gizlilik sempozyumu (s. 3-18). ıeee.
  • Tolido, R., Frank, A., Delabarre, L., & Cherian, S. (2020). Reinventing cybersecurity with artificial intelligence: the new frontier in digital security. amsterdam: capgemini researchınstitute.
  • Aslan, F. (2022, Nisan 14). iskulubu. https://iskulubu.com/manset/yapay-zekanin-en-onemli-5-avantaji-ve-dezavantaji/ Cimpanu, C. (2020, Ekim 17).
  • https://www.zdnet.com/article/first-death-reported-following-a-ransomware-attack-on-a-german-hospital/iisbf gelisim haber. (2021).
  • https://iisbf.gelisim.edu.tr/bolum/isletme-37/haber/stanford-universitesi-2021-yili yapay-zeka-raporu-yayimlandi McElfresh, M. (2016).https://theconversation.com/cyberattack-on-ukraine-grid-heres-how-it-worked-and-perhaps-why-it-was-done-52802
  • Voss RF, Clarke J. (1986) Algorithmic Musical Composition, Silver Burdett Press, London.
  • Zabierowski W, Napieralski A (2003) Chords classification in tonal music. Journal of Environment Studies 10(5): 50-53.
  • Abiewskiro A, Moplskiiera Z. (2008) The Problem Of Grammar Choice For Verification. TCSET of the International Conference, House of Lviv Polytechnic National University, pp.19-23.
  • Healthwise Knowledgebase (1998) US Pharmacopeia, Rockville. http://www.healthwise.org. Accessed 21 Sept 1998
There are 22 citations in total.

Details

Primary Language Turkish
Subjects Computer Software
Journal Section PAPERS
Authors

Muharrem Tuncay Gençoğlu 0000-0002-8784-9634

Publication Date October 10, 2022
Submission Date September 8, 2022
Acceptance Date September 16, 2022
Published in Issue Year 2022 Volume: IDAP-2022 : International Artificial Intelligence and Data Processing Symposium

Cite

APA Gençoğlu, M. T. (2022). IPS Sistemlerde Yapay Zekânın Son Beş Yıldaki Gelişimi. Computer Science, IDAP-2022 : International Artificial Intelligence and Data Processing Symposium, 211-218. https://doi.org/10.53070/bbd.1172803

The Creative Commons Attribution 4.0 International License 88x31.png is applied to all research papers published by JCS and

A Digital Object Identifier (DOI) Logo_TM.png is assigned for each published paper