Artificial Intelligence Focused Cyber Risk and Security Management

Öz

While arming AI and machine learning for cybersecurity is still in its early stages, large-scale firms and organizations continuously develop autonomous defense capabilities that include AI and machine learning to protect their security systems and applications. In addition, intelligent cyber attackers have started to use independent AI algorithms, continuously developing their capabilities due to the advantages of automatically uncovering new security vulnerabilities for achieving their illegal goals. For this reason, attack tools that learn by themselves, automatically scan vulnerabilities, discover proper techniques to exploit and disable firewalls and attack directly have become very sophisticated. On the other hand, AI can play a critical role in risk management and providing more effective and agile service by automatically detecting risks and control vulnerabilities in the dynamic IT environment and reporting their probability and impact degrees. Therefore, while risk management can become more effective with AI, the risks exposed through AI have also become more sophisticated. This study investigates from literature and sectoral reports the role of AI in cybercrime and cybersecurity and the manageability of risks in the cyber area through AI algorithms. The study explores how serious the AI-based dangers and threats are and how they can help improve an organization's security posture and risk appetite against AI-powered advanced persistent threats (APT).

Anahtar Kelimeler

• artificial intelligence
• risk management
• IT risks
• risk automation
• smart MIS

Yapay Zeka Odaklı Siber Risk ve Güvenlik Yönetimi

Öz

Yapay zekayı (YZ) ve makine öğrenimini siber güvenlik için silahlandırmak hala erken aşamalarda olsa da büyük ölçekli firmalar ve kuruluşlar, güvenlik sistemlerini ve uygulamalarını korumak için YZ ve makine öğrenimini içeren özerk savunma yeteneklerini geliştirmeye çalışmaktadırlar. Bunun yanı sıra, siber saldırganlar da yetenek ve araçlarını sürekli geliştirirken yeni güvenlik açıklarını ortaya çıkarmak ve yasa dışı amaçlarına ulaşmak için sağladığı avantajlardan dolayı otonom YZ algoritmalarını kullanmaya başlamışlardır. Bu nedenle kendi kendisine öğrenen, zafiyetleri otomatik olarak tarayarak hangi tekniklerle suiistimal yapılmasının ve güvenlik duvarlarının etkisiz hale getirilebileceğinin nasıl olanaklı olduğunu raporlayan ve/veya doğrudan saldırıya geçebilen otonom saldırı araçları büyük bir risk olarak çok sofistike hale gelmiştir. Buna karşın dinamik BT ortamındaki riskleri ve kontrol zafiyetlerini otomatik olarak algılayarak ve bunların olasılık ve etki derecelerini raporlayarak risk yönetiminin de daha etkili olarak güvenlik ve savunma hizmetine destek sağlamasında da YZ kritik roller oynayabilmektedir. Dolayısıyla YZ ile risk yönetimi daha etkin hale gelebilirken YZ üzerinden maruz kalınan riskler de daha sofistike hale gelmiştir. Bu çalışma, YZ’ nin siber suç ve siber güvenlikteki rolünü, bu alandaki risklerin YZ üzerinden yönetilebilirliğini literatür ve sektörel raporların incelenmesi yoluyla araştırmaktadır. Çalışmada, YZ tabanlı risk ve tehditlerin ne kadar ciddi olduğu yanı sıra, bir kuruluşun YZ destekli gelişmiş kalıcı tehditlere (APT) karşı güvenlik duruşunu ve risk iştahını iyileştirmeye nasıl yardımcı olunabileceği teknik olarak ortaya konulmaktadır.

Anahtar Kelimeler

• yapay zeka
• risk yönetimi
• BT riskleri
• risk otomasyonu
• akıllı YBS

Kaynakça

1. Abegunde, J., Xiao, H., & Spring, J. (2016) A dynamic game with adaptive strategies for IEEE 802.15.4 and IoT. 2016 IEEE Trustcom/ BigDataSE/ISPA, 473–480. https://doi.org/10.1109/TrustCom. 2016.0099
2. Aldemir, C. & Kaya, M. (2020). Bilgi Toplumu, Siber Güvenlik ve Türkiye Uygulamaları. Kamu Yönetimi ve Politikaları Dergisi, 1 (1), 6-27. Retrieved from https://dergipark.org.tr/tr/pub/kaypod/issue/56116/726431
3. Al-Turjman F (2020) Intelligence and security in big 5G-oriented IoNT: an overview. Futur Gener Comput Syst 102:357–368. https://doi.org/10.1016/j.future.2019.08.009
4. Anagnostopoulos, C., & Hadjiefthymiades, S. (2019) A Spatio-temporal data imputation model for supporting analytics at the edge. Digital transformation for a sustainable society in the 21st century: 18th IFIP WG 6.11 conference on E-Business, E-Services, and E-Society, I3E 2019, Trondheim, Norway, September 18–20, 2019, Proceedings, 11701, 138
5. Archer (2021a) Fraud Detection: How to use machine learning in fintech?, https://archer-soft.com/blog/fraud-detection-how-use-machine-learning-fintech
6. Archer (2021b) 6 Artificial Intelligence use cases in financial services, https://archer-soft.com/blog/6-artificial-intelligence-use-cases-financial-services
7. Archer, (2021c) How AI is changing the risk management? Source: https://archer-soft.com/blog/how-ai-changing-risk-management
8. Bablix, (2021) Balbix BreachControl, https://www.balbix.com/product-overview/

9. Baloglu, A, Kılıç, S, Binay, A, Tükel, D. (2020). Endüstriyel Üretim Tesisleri İçin Asistan Robot Araştırması ve Analizi. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 4 (1) , 13-27 . DOI: 10.33461/uybisbbd.620575
10. Balduzzi M., Maggi F., (2017) DefPloreX: A Machine-Learning Toolkit for Large-scale eCrime Forensics, Trendmicro, https://blog.trendmicro.com/trendlabs-security-intelligence/ defplorex-machine-learning-toolkit-large-scale-ecrime-forensics/
11. Barker K, Lambert JH, Zobel CW, Tapia AH, Ramirez-Marquez JE, Albert L, Nicholson CD, Caragea C (2017) Defining resilience analytics for interdependent cyber-physical-social networks. Sustain Resilient Infrastruct 2(2):59–67. https://doi.org/10.1080/23789689. 2017.1294859
12. Barrett, B. (2016) IBM's Watson Has a New Project: Fighting Cybercrime, Wired, https://www.wired.com/2016/05/ibm-watson-cybercrime/
13. Bashir H, Lee S, Kim KH (2019) Resource allocation through logistic regression and multicriteria decision-making method in IoT fog computing. Trans Emerg Telecommun Technol. https://doi.org/10. 1002/ett.3824
14. Berman D, Buczak A, Chavis J, Corbett C (2019) A survey of deep learning methods for cybersecurity. Information 10(4):122. https://doi.org/10.3390/info10040122
15. Blanco-Filgueira B, Garcia-Lesta D, Fernandez-Sanjurjo M, Brea VM, Lopez P (2019) Deep learning-based multiple object visual tracking on embedded system for IoT and mobile edge computing applications. IEEE Internet Things J 6(3):5423–5431. https://doi.org/10.1109/JIOT.2019. 2902141
16. Calix R.A., Singh S.B., Chen T., Zhang D. and Tu M., (2020) Cyber Security Tool Kit (CyberSecTK): A Python Library for Machine Learning and Cyber Security, Information 2020, 11, 100; doi:10.3390/info11020100
17. Cao, B., Zhang, L., Li, Y., Feng, D., & Cao, W. (2019) Intelligent offloading in multi-access edge computing: a state-of-the-art review and framework. In: IEEE communications magazine. Institute of Electrical and Electronics Engineers Inc., (vol. 57, issue 3, pp. 56– 62). https://doi.org/10.1109/MCOM.2019.1800608
18. CFR, (2017) The Cybersecurity Vulnerabilities to Artificial Intelligence, Net Politics, https://www.cfr.org/blog/cybersecurity-vulnerabilities-artificial-intelligence
19. Cui Q, Gong Z, Ni W, Hou Y, Chen X, Tao X, Zhang P (2019) Stochastic online learning for mobile edge computing: learning from changes. IEEE Commun Mag 57(3):63–69. https://doi.org/10.1109/ MCOM. 2019.1800644
20. Deloitte, (2020) Smart cyber: How AI can help manage cyber risk, https://www2.deloitte.com/ content/dam/Deloitte/ca/Documents/risk/ca-en-smart-cyber-pov-aoda.pdf
21. Demertzis K., Iliadis L. (2015) A Bio-Inspired Hybrid Artificial Intelligence Framework for Cyber Security. In: Daras N., Rassias M. (eds) Computation, Cryptography, and Network Security. Springer, Cham. https://doi.org/10.1007/978-3-319-18275-9_7
22. Diro AA, Chilamkurti N (2018) Distributed attack detection scheme using deep learning approach for Internet of Things. Futur Gener Comput Syst 82:761–768. https://doi.org/10.1016/ j.future.2017.08. 043
23. FAIR (2017) What is a cyber value-at-risk model? http://www.fairinstitute.org /blog/what-is-a-cyber-value-at-risk-model
24. Ganti, V. (2018). How Machine Learning and AI in Cybersecurity is Shaping IT, Biztech Magazine, https://biztechmagazine.com/article/2018/06/role-artificial-intelligence-cybersecurity
25. Gebremariam, A. A., Usman, M., & Qaraqe, M. (2019) Applications of artificial intelligence and machine learning in the area of SDN and NFV: a survey. 16th international multi-conference on systems, sig nals and devices, SSD 2019, 545–549. https://doi.org/10.1109/SSD. 2019.8893244
26. Giles, M. (2018) AI for cybersecurity is a hot new thing—and a dangerous gamble, Technology Review, https://www.technologyreview.com/2018/08/11/141087/ai-for-cybersecurity-is-a-hot-new-thing-and-a-dangerous-gamble/
27. Guo Y., Cao H., Han S., Sun Y., Bai Y. (2018) Spectral-spatial hyperspectral image classification with K-nearest neighbor and guided filter. IEEE Access 6:18582–18591. https://doi.org/10.1109/ ACCESS.2018. 2820043
28. Hu R., Wen S., Zeng Z., Huang T. (2017) A short-term power load fore casting model based on the generalized regression neural network with decreasing step fruit fly optimization algorithm. Neurocomputing 221:24–31. https://doi.org/10.1016/j.neucom. 2016.09.027
29. IBM (2021) QRadar Advisor with Watson, https://www.ibm.com/in-en/products/ cognitive-security-analytics Intercept, (2020) Stop Unknown Threats, Sophos, https://www.sophos.com/en-us/medialibrary/PDFs/factsheets/sophos-intercept-x-dsna.pdf
30. Kaloudi N. & Li J., (2020). The AI-Based Cyber Threat Landscape: A Survey. ACM Comput. Surv. 53, 1, Article 20 (May 2020), 34 pages. DOI: https://doi.org/10.1145/3372823
31. Küçük, D, Arıcı, N . (2018). Doğal dil işlemede derin öğrenme uygulamaları üzerine bir literatür çalışması. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 2 (2) , 76-86 . Retrieved from https://dergipark.org.tr/tr/pub/uybisbbd/issue/41787/443574
32. Li H., Ota K. & Dong M. (2018) Learning IoT in edge: deep learning for the Internet of Things with edge computing. IEEE Netw 32(1):96–101. https://doi.org/10.1109/ MNET.2018.1700202
33. Madrid, S., (2020) Juniper Strengthens Connected Security Portfolio with New Risk-Based Access Control Capabilities and Remote Access VPN, Juniper, https://blogs. juniper.net/en-us/security/juniper-strengthens-connected-security-portfolio-with-new-risk-based-access-control-capabilities-and-remote-access-vpn
34. Malhotra Y. (2018) Cognitive computing for anticipatory risk analytics in intelligence, surveillance, & reconnaissance (ISR): model risk management in artificial intelligence & machine learning (presentation slides). SSRN Electron J. https://doi.org/10.2139/ssrn.3111837
35. Newman, L. H., (2018) AI Can Help Cybersecurity—If It Can Fight Through the Hype, Wired, https://www.wired.com/story/ai-machine-learning-cybersecurity/
36. Nguyen T.G., Phan TV, Nguyen BT, So-In C, Baig ZA, Sanguanpong S (2019) SeArch: a collaborative and intelligent NIDS architecture for SDN-based cloud IoT networks. IEEE Access 7:107678–107694. https://doi.org/10.1109/ACCESS.2019.2932438
37. Park D., Kim S., An Y., Jung J-Y. (2018) LiReD: a light-weight real-time fault detection system for edge computing using LSTM recurrent neural networks. Sensors 18(7):2110. https://doi.org/ 10.3390/s18072110
38. Porambage, P., Kumar, T., Liyanage, M., Partala, J., Lovén, L., Ylianttila, M., & Seppänen, T. (2019) Sec-edgeAI: AI for edge security vs. security for edge AI BrainICU-measuring brain function during intensive care view project ECG-based emotion recognition view project Sec-EdgeAI. https://www.researchgate.net/publication/330838792
39. PwC, (2020) Model Risk Management of AI and Machine Learning Systems, https://www.pwc.co.uk/data-analytics/documents/model-risk-management-of-ai-machine-learning-systems.pdf
40. Radanliev P, De Roure D, Nurse JRC, Mantilla Montalvo R, Cannady S, Santos O, Maddox L, Burnap P, Maple C (2020a) Future developments in standardization of cyber risk in the Internet of Things (IoT). SN Appl Sci 2(2):1–16. https://doi.org/10.1007/s42452-019-1931-0
41. Radanliev, Petar & De Roure, David & Page, Kevin & Van Kleek, Max & Santos, Omar & Maddox, la & Burnap, Pete & Anthi, Eirini & Maple, Carsten. (2020). Design a dynamic and self-adapting system, supported with artificial intelligence, machine learning, and real-time intelligence for predYun.ive cyber risk analytics in extreme environments – cyber risk in the colonization of Mars.
42. Roopak, M., Yun Tian, G., & Chambers, J. (2019) Deep learning models for cybersecurity in IoT networks. 2019 IEEE 9th annual computing and communication workshop and conference, CCWC 2019, 452– 457. https://doi.org/10.1109/CCWC.2019.8666588
43. Sanford, A., & Moosa, I. (2015). Operational risk modeling and organizational learning in structured finance operations: A Bayesian network approach. Journal of the Operational Research Society, 66(1), 86–115.
44. Sangaiah A.K., Medhane D.V., Han T., Hossain M.S., Muhammad G. (2019) Enforcing position-based confidentiality with machine learning paradigm through mobile edge computing in real-time industrial informatics. IEEE Trans Ind Inform 15(7):4189–4196. https://doi.org/10. 1109/TII.2019.2898174
45. Sedjelmaci H., Guenab F., Senouci S., Moustafa H., Liu J. & Han S., (2020) "Cyber Security Based on Artificial Intelligence for Cyber-Physical Systems," in IEEE Network, vol. 34, no. 3, pp. 6-7, May/June https://doi.org/10.1109/MNET.2020.9105926 .
46. Stigsifter, (2020) A machine learning tool that ranks strings based on their relevance for malware analysis. Fireeye, https://github.com/fireeye/stringsifter
47. Sultana N., Chilamkurti N., Peng W., Alhadad R. (2019) Survey on SDN based network intrusion detection system using machine learning approaches. Peer-to-Peer Netw Appl 12(2):493–501. https://doi.org/10.1007/s12083-017-0630-0
48. Sun, D., Wu, Z., Wang, Y., Lu, Q., & Hu, B. (2019) Risk prediction for imbalanced data in cybersecurity: a Siamese network-based deep learning classification framework. Proceedings of the international joint conference on neural networks, 2019-July, 1–8. https://doi.org/10.1109/ IJCNN.2019.8852030
49. Syafrudin M, Fitriyani N, Alfian G, Rhee J (2018) An affordable, fast early warning system for edge computing in assembly line. Appl Sci 9(1):84. https://doi.org/10.3390/app9010084
50. Symantech, (2018) Targeted Attack Analytics, https://docs.broadcom.com/doc/targeted-attack-analytics-en
51. Takaoğlu, M , Özer, Ç . (2019). Saldırı Tespit Sistemlerine Makine Öğrenme Etkisi . Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 3 (1), 11-22. DOI: 10.33461/uybisbbd.558192
52. Thompson, M.F., Vidas, T., (2018), CGC monitor: A vetting system for the DARPA cyber grand challenge, Digital Investigation, https://doi.org/10.1016/j.diin.2018.04.016
53. Tung L., (2017) Elon Musk: Regulate AI now, before it's too late, ZDNET, https://www.zdnet.com/article/elon-musk-regulate-ai-now-before-its-too-late/
54. Ullah I, Ahmed S, Mehmood F, KimD (2019) Cloud-based IoT network virtualization for supporting dynamic connectivity among connected devices. Electronics 8(7):742. https://doi.org/10.3390/electronics8070742
55. Vectra, (2021) Cognito Platform-Network detection and response built on artificial intelligence https://www.vectra.ai/products/cognito-platform
56. Vinayakumar R, Alazab M, Soman KP, Poornachandran P, Al-Nemrat A, Venkatraman S (2019) Deep learning approach for intelligent intrusion detection system. IEEE Access 7:41525–41550. https://doi.org/10.1109/ACCESS.2019.2895334
57. Wang J, Hu J, Min G, Zhan W, Ni Q, Georgalas N (2019a) Computation offloading in multi-access edge computing using a deep sequential model based on reinforcement learning. IEEE Commun Mag 57(5): 64–69. https://doi.org/10.1109/MCOM.2019.1800971
58. Wang X, Han Y, Wang C, Zhao Q, Chen X, Chen M (2019b) In-edge AI: intelligent sizing mobile edge computing, caching and communication by federated learning. IEEE Netw 33(5):156–165. https://doi.org/10.1109/MNET.2019.1800286
59. Yamin M. M., Ullah M., Ullah H., & Katt B., (2021) Weaponized AI for cyberattacks, Journal of Information Security and Applications, Volume 57, 102722, ISSN 2214-2126, https://doi.org/10.1016/j.jisa.2020.102722.
60. Yıldız, D. (2021). Bilgi Yönetiminde Kural Tabanlı Uzman Sistem Geliştirme Adımları Ve Başarı Faktörleri. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 5 (1), 28-43. DOI: https://doi.org/10.33461/uybisbbd.913513
61. Yin H, Xue M, Xiao Y, Xia K, Yu G (2019) Intrusion detection classification model on an improved k-dependence Bayesian network. IEEE Access 7:157555–157563. https://doi.org/10.1109/ ACCESS. 2019.2949890
62. Zhang, D., Bao, W., Fang, T., Liang, W., Zhou, W., Ma, L., Gao, X., & Niu, L. (2019) Edge task allocation scheme based on data classification. Proceedings – 2019 5th international conference on big data and information analytics, BigDIA 2019, 132–138. https://doi.org/10.1109/ BigDIA.2019.8802859