Yapay Zeka Teknolojilerinin KBRN Adli Bilimlerinde Kullanımı

Abstract

Kimyasal, Biyolojik, Radyolojik ve Nükleer (KBRN) olayları halk sağlığı, çevre ve ulusal güvenlik için tehdit oluşturmaktadır. KBRN adli soruşturmaları ve analizleri saldırganları tespit etmek ve ikincil saldırıları önlemek için hayati öneme sahiptir. Ancak KBRN olayları oldukça karmaşıktır ve geleneksel adli yöntemler bazen yetersiz kalmaktadır. KBRN adli bilimleri ve yapay zekanın (YZ) kesişimi sorunlara yaratıcı ve etkili çözümler sunmaktadır. Bu çalışma YZ teknolojilerinin YZ ile ilgili adli bilimlerde kullanımını araştırmaktadır. Örneğin, derin öğrenme, makine öğrenmesi, sinir ağları ve olasılıksal yaklaşımlar gibi yöntemler karmaşık KBRN kanıtlarının analizinde sıklıkla kullanılmaya başlanmıştır. Bu şekilde suç mahalli verileri daha hızlı ve daha doğru bir şekilde analiz edilebilmektedir. Yapay zeka tabanlı sistemlerin düşük kaliteli görüntüleri iyileştirme, alışılmadık davranışları tespit etme ve ses ve videoyu daha hassas bir şekilde analiz etmedeki hataları azaltmadaki etkisi oldukça etkileyicidir. Sanal otopsi, genetik profilleme, metagenomik algoritmalar ve RNA ekspresyon analizleri gibi uygulamalar da soruşturmalar için daha yaygın hale gelmektedir. Ayrıca, suç mahallerini simüle etmek ve kararları iyileştirmek için yeni test edilen teknolojiler arasında robotlar, sensör füzyonu, dijital ikizler ve artırılmış gerçeklik gibi yeni nesil teknolojiler yer alıyor. Öte yandan, bu teknolojiler bazı riskler ve zorluklar da getiriyor. Kişisel ve hassas verilerin korunması ve dijital dolandırıcılıkla (deepfake gibi) mücadele gibi konular ön plana çıkıyor. Ayrıca, AI sonuçlarının yasal davalarda nasıl kullanılabileceği konusunda bir fikir birliği yok. AI, adli bilimin geleneksel standart prosedürlerinde önemli değişiklikler getirme potansiyeline sahip. Sürü zekası, dijital ikizler ve otonom sistemler gibi yeni teknolojiler, acil durum ekiplerinin daha hızlı ve gecikmeden hareket etmesine yardımcı olabilir. Psikofizyolojik izleme gibi AI araçları da ekiplerin birlikte çalışma ve karar alma şeklini iyileştirebilir. Bu değişim yalnızca daha iyi eğitim, etik ve küresel iş birliği ile mümkündür.

Keywords

• KBRN
• Adli Bilimler
• Yapay Zeka
• Acil Müdahale

Use of Artificial Intelligence Technologies in CBRN Forensic Sciences

Abstract

Chemical, Biological, Radiological, and Nuclear (CBRN) incidents pose a threat to public health, the environment, and national security. CBRN forensic investigations and analyses are vital to detecting attackers and preventing secondary attacks. However, CBRN incidents are very complex and traditional forensic methods are sometimes inadequate. The intersection of CBRN forensics and artificial intelligence (AI) offers creative and effective solutions to the problems. This study explores the use of AI technologies in CBRN-related forensic science. For example, methods such as deep learning, machine learning, neural networks, and probabilistic approaches have become frequently used in the analysis of complex CBRN evidence. In this way, crime scene data can be analyzed faster and more accurately. The impact of AI-based systems in improving low-quality images, detecting unusual behaviors, and reducing errors in analyzing audio and video more precisely is quite impressive. Applications such as virtual autopsy, genetic profiling, metagenomic algorithms, and RNA expression analyses are also becoming more common for investigations. In addition, new generation technologies such as robots, sensor fusion, digital twins and augmented reality are among the newly tested technologies to simulate crime scenes and improve decisions. On the other hand, these technologies also bring some risks and challenges. Issues such as protecting personal and sensitive data and combating digital fraud (such as deepfakes) come to the fore. In addition, there is no consensus on how AI results can be used in legal cases. AI has the potential to bring significant changes to the traditional standard procedures of forensic science. New technologies such as swarm intelligence, digital twins and autonomous systems can help emergency teams act faster and without delay. AI tools such as psychophysiological monitoring can also improve the way teams work together and make decisions. This change is only possible with better training, ethics and global cooperation.

Keywords

• CBRN
• Forensic Sciences
• Artificial Intelligence
• Emergency Response

References

1. Amorim, A. M. B., Piochi, L. F., Gaspar, A. T., Preto, A. J., Rosário-Ferreira, N., & Moreira, I. S. (2024). Advancing drug safety in drug development: Bridging computational predictions for enhanced toxicity prediction. Chemical Research in Toxicology, 37(6), 827–849 . https://doi.org/10.1021/acs.chemrestox. 3c00352
2. Avican, K., Aldahdooh, J., Togninalli, M., Mahmud, A. K. M. F., Tang, J., Borgwardt, K. M., Rhen, M., & Fällman, M. (2021). RNA atlas of human bacterial pathogens uncovers stress dynamics linked to infection. Nature Communications, 12(1), Article 3282 . https://doi.org/10.1038/s41467-021-23588-w
3. Bhardwaj, J., Goyal, K., Malsawmzuali, C., & Narula, A. (2025). Revolutionizing forensic science: The role of artificial intelligence in evidence analysis. International Journal of Interdisciplinary Approaches in Psychology, 3(1).
4. Bonicelli, A., Bonneau, N., Cattaneo, C., Balsamo, L., Pittner, S., & Procopio, N. (2023). ForensOMICS: Multi-omics for post-mortem interval estimation in human bones. eLife, 12, Article e83658.
5. Cheng, H., Zhang, X., & Li, Y. (2022). Real-time 3D modeling applications in forensic digital twin investigations. IEEE Transactions on Visualization and Computer Graphics, 28(5), 2341–2352. https://doi.org/10.1109/TVCG.2022.3145678
6. Chiu, C. Y., & Miller, S. A. (2019). Clinical metagenomics. Nature Reviews Genetics, 20(6) , 341–355. https://doi.org/ 10.1038/s41576-019-0113-7
7. Christie, E. H. (2020). NATO decision-making in the age of big data and artificial intelligence. NATO Allied Command Transformation. https://www.act.nato.int/wpcontent/uploads/2024/07/20210301_AC-2020_Final-Report.pdf
8. Committee on Legal Affairs and Human Rights (AS/Jur). (2021). Poisoning of Alexei Navalny report (Rapporteur: Mr. Jacques Maire). Alliance of Liberals and Democrats for Europe.

9. Dereli, C., & Dağlıoğlu, N. (2024). Fentanyl and fentanyl subgroups as chemical weapons. Hacettepe Journal of Biology and Chemistry, 52(5) , 363–372. https://doi.org/10.15671/ hjbc.1578899
10. Devassy, B. M., & George, S. (2021). Forensic analysis of beverage stains using hyperspectral imaging. Scientific Reports, 11(1), Article 6512. https://doi.org/10.1038/ s41598-021-85737-x
11. Dotson, G. S., Maier, A., & Clark, L. (2015). A decision support framework for characterizing and managing dermal exposures to chemicals during emergency management and operations. Journal of Emergency Management, 13(3), 227–238. https://doi.org/10.5055/jem.2015.0236
12. Duman Kantarcıoğlu, V. (2023). Radyolojik ve nükleer terörizm. In A. Pakdemirli & S. Sezigen (Eds.), KBRN: Kimyasal, biyolojik, radyolojik ve nükleer (pp. n.d.). EMA Tıp Kitapevi.
13. Dunsin, D., Ghanem, M. C., Ouazzane, K., & Vassilev, V. (2023). A comprehensive analysis of the role of artificial intelligence and machine learning in modern digital forensics and incident response. [Unpublished manuscript].
14. El-Din, E. A. (2022). Artificial intelligence in forensic science: Invasion or revolution? ESCTJ, 10(2).
15. Farber, S. (2024). AI in terrorism sentencing: Evaluating predictive accuracy and ethical implications. Criminal Justice Studies, 37(4).
16. Guicheteau, J. A. (2024). Chemical biological radiological nuclear & explosive (CBRNe) sensing. North Atlantic Treaty Organization Science & Technology Organization.
17. Hewes, M. (2023). How artificial intelligence will change information and computer security in the nuclear world. IAEA Bulletin. https://www.iaea.org/bulletin/howartificial-intelligence-will-change-information-and-computer-security-in-the-nuclearworld
18. Kassem, M. A., & Lodhi, K. (2024). Revolutionizing forensic science: The role of artificial intelligence and machine learning. Journal of Artificial Intelligence, Machine Learning, and Bioinformatics, 2024, 7–15. https://doi.org/10.5147/jaimlb.vi.255
19. Kendler, S., & Fishbain, B. (2020). Crime scene investigation using hyperspectral imaging–Opportunities and challenges. International Journal of Forensic Sciences, 5(4) , Article 000205. https://doi.org/10.23880/ijfsc -16000205
20. Lin, Z., & Chou, W.-C. (2022). Machine learning and artificial intelligence in toxicological sciences. Toxicological Sciences, 189(1) , 7–19. https://doi.org/10.1093/toxsci/kfac 075
21. Liu, R. (2021). Application of machine learning in effective identification of chemical agents [Undergraduate honors thesis, Honors Research in Chemistry]. https://github. com/rexpository/CNN-ChemicalIdentifier
22. Maggi, F., Zanero, S., & Iozzo, V. (2008). Seeing the invisible: Forensic uses of anomaly detection and machine learning. ACM SIGOPS Operating Systems Review, 42(3) , 51–58 . https://doi.org/ 10.1145/1368506.1368514
23. Mandalapu, V., Elluri, L., Vyas, P., & Roy, N. (2023). Crime prediction using machine learning and deep learning: A systematic review and future directions. IEEE Access, 11, 60153–60170. https://doi.org/10.1109/ACCESS.2023.3286344
24. Marymount University. (2025, May 15). The role of AI in forensics. https://marymount. edu/blog/the-role-of-ai-in-forensics/
25. Organisation for the Prohibition of Chemical Weapons. (2001, June). The sarin gas attack in Japan and the related forensic investigation. OPCW News. https://www.opcw.org/ media-centre/news/2001/06/sarin-gas-attack-japan-and-related-forensic-investigation
26. Organisation for the Prohibition of Chemical Weapons. (2018). Incident in Salisbury: Technical assistance provided by OPCW related to toxic chemical incidents in Salisbury and Amesbury.
27. Organisation for the Prohibition of Chemical Weapons. (2020). OPCW issues report on technical assistance requested by Germany.
28. Owen, R. (2016). The Litvinenko inquiry: Report into the death of Alexander Litvinenko. House of Commons. https://www.gov.uk/government/publications/the-litvinenkoinquiry-report-into-the-death-of-alexander-litvinenko
29. PBS. (2017). Kim Jong-nam carried the antidote to the poison that killed him. https://www. pbs.org/wgbh/frontline/article/king-jong-nam-carried-the-antidote-to-the-poison-thatkilled-him/
30. Sessa, F., Esposito, M., Cocimano, G., Sablone, S., Karaboue, M. A. A., Chisari, M., Albano, D. G., & Salerno, M. (2024). Artificial intelligence and forensic genetics: Current applications and future perspectives. Applied Sciences, 14(5) , Article 2113.
31. SIFS India. (2024, August 25). Revolutionizing forensic ballistics: Cutting-edge technologies and their impact. https://www.sifs.in/events/blog-details/forensicballistics-emanuel
32. Smyth, D. L., Glavin, F. G., & Madden, M. G. (2018). Using a game engine to simulate critical incidents and data collection by autonomous drones. IEEE Games, Entertainment, and Media Conference (GEM). https://doi.org/10.1109/GEM.2018.8516527
33. Stalans, L. J., & Lindell, M. (2018). The impact of artificial intelligence tools on criminal psychological profiling. International Journal of Academic Research in Psychology, 11(1) , 1–15.
34. Tortora, L., Meynen, G., Bijlsma, J., Tronci, E., & Ferracuti, S. (2020). Neuroprediction and A.I. in forensic psychiatry and criminal justice: A neurolaw perspective. Frontiers in Psychology, 11, Article 220. https://doi.org/10.3389/fpsyg.2020.00220
35. United Nations Interregional Crime and Justice Research Institute, & International Criminal Police Organization. (2019). Artificial intelligence and robotics for law enforcement. INTERPOL.
36. U.S. Army. (2015, December 4). Project JUPITR early warning system can save lives. https://www.army.mil/article/159494/project_jupitr_early_warning_system_can_ save_lives
37. U.S. Department of Homeland Security, The Office of Intelligence and Analysis. (2025). 2025 homeland threat assessment report.
38. U.S. Department of Justice. (2010, February 19). Amerithrax investigative summary.
39. Vodanović, M., Subašić, M., Milošević, D., Galić, I., & Brkić, H. (2023). Artificial intelligence in forensic medicine and forensic dentistry. Journal of Forensic OdontoStomatology, 41(2) , 30–41. https://pubmed.ncbi.nlm.nih.gov/ 37634174
40. Wang, C., Wang, C., Huang, Z., & Xu, S. (2020). Materials and structures toward soft electronics for wearable health monitoring. Advanced Materials, 32(15), Article 1901985 . https://doi.org/10.1002/adma. 201901985
41. Yang, L., Liu, Y., Zhao, J., & Zhang, Y. (2023). Forensic data analytics for anomaly detection in evolving networks. arXiv. https://arxiv.org/abs/2308.09171
42. Zhou, L., Xu, X., Xu, Y., & Li, G. (2021). Artificial intelligence in smart wearables: A review. IEEE Sensors Journal, 21(22), 24677–24691. https://doi.org/10.1109/ JSEN.2021.3102764