Abstract

Dual-use research (DUR) serves both scientific and practical purposes, yet it is susceptible to misuse for harmful applications. Effectively classifying DUR is essential to protect sensitive information while enabling beneficial research to continue. Artificial Intelligence (AI), particularly ML Classification Models (MLCMs), has emerged as a powerful tool for this complex classification challenge. This systematic review examines AI's effectiveness in identifying and classifying dual-use and SDUR, with emphasis on MLCMs and Natural Language Processing (NLP) techniques. Analysis of English-language articles from 2006–2023 across seven databases, including PubMed, Scopus, Google Scholar, arXiv, IEEE Xplore, and Springer Link, yielded 101 relevant studies after screening 8,037 initial results. The findings reveal widespread use of ML techniques, primarily Decision Trees, Naïve Bayes, Random Forests, and Support Vector Machines. NLP methods, especially Topic Modeling and Sentiment Analysis, were frequently employed. These models demonstrated effectiveness in classifying DUR, suggesting the potential for automated identification systems. However, the review identifies several areas for improvement, including data quality, standardization, and reporting transparency. While acknowledging DUR's contributions to scientific progress, the study emphasizes the importance of ethical considerations and safeguards when implementing automated classification systems.

References

• Acosta, M., Coronado, D., & Marín, R. (2011). Potential dual-use of military technology: Does citing patents shed light on this process? Defence and Peace Economics, 22(3), 335–349. https://doi.org/10.1080/10242694.2010.491681
• Arrison, T., & Sloan, S. S. (2011). Examining core elements of international research collaboration: Summary of a workshop. National Academies Press.
• Atlas, R. M., & Dando, M. (2006). The dual-use dilemma for the life sciences: Perspectives, conundrums, and global solutions. Biosecurity and Bioterrorism: Biodefense Strategy, Practice, and Science, 4(3), 276–286.
• Awodi, N. J., Liu, Y. K., Ayodeji, A., & Adibeli, J. O. (2021). Expert judgement-based risk factor identification and analysis for an effective nuclear decommissioning risk assessment modeling. Progress in Nuclear Energy, 136, 103733. https://doi.org/10.1016/j.pnucene.2021.103733
• Ayinla, B. I. (2023). Index mapped ordinal encoding method for federated machine learning in crime detection. University of Ibadan Journal of Science and Logics in ICT Research, 9(1), 15–31.
• Ayinla, B. I. (2024a). Development of LR-multi predicting cross-validation model for an imbalanced dataset in a flood susceptible area. International Journal of Computer Applications, 975(8887), 45–53.
• Ayinla, B. (2024b). Multifactor authentication prevent store-xss server model for effective mitigation against cross-site scripting. Nigeria Computer Society (NCS) Conference Proceedings, 36(1), 28–34.
• Ayinla, B. I., & Akinola, S. O. (2021). An improved ensemble model using random forest branch clustering optimisation approach. University of Ibadan Journal of Science and Logics in ICT Research, 7(2), 28–32.
• Ayinla, B., Ferreira, D. D., & Silva, F. O. (2026). An integrated wavelet DAG-CNLASCM structure with recurrent neural networks for climate vulnerabilities prediction. Advances in Artificial Intelligence and Applications (AAAE), 14(2), 115–132. https://doi.org/10.1109/AAAE.2026.1043219
• Beaudrie, C. E. H., Kandlikar, M., & Ramachandran, G. (2016). Using expert judgment for risk assessment. In Assessing nanoparticle risks to human health (2nd ed., pp. 91–119). Elsevier. https://doi.org/10.1016/B978-0-323-35323-6.00005-0
• Board of Science and Education. (2004). Biotechnology, weapons and humanity II. British Medical Association (BMA), London.
• Cameron, G., & Pate, J. (2001). Covert biological weapons attacks against agricultural targets: Assessing the impact against U.S. agriculture. Terrorism and Political Violence, 13(3), 61–82.
• Cardona-Álvarez, Y. N., Álvarez-Meza, A. M., & Castellanos-Dominguez, G. (2025). Revolutionizing data exchange through intelligent automation: Insights and trends. Computers, 14(5), 194.
• Carpenter, M. P., Narin, F., & Woolf, P. (1981). Citation rates to technologically important patents. World Patent Information, 3(4), 160–163. https://doi.org/10.1016/0172-2190(81)90098-3
• Carvalho, S., Soares, F., Rita, P., & Rocha, M. (2023). Machine learning for dual-use research detection: A scoping review. Technological Forecasting and Social Change, 187, 122085.
• Chahal, A., & Gulia, P. (2021). Machine learning and deep learning. International Journal of Innovative Technology and Exploring Engineering, 8(12), 4910–4914.
• Chang, L., Qiu, J., & Miao, H. (2023). Identifying and classifying dual-use research of concern: A machine learning and topic modeling approach. Science and Engineering Ethics, 29(2), 721–743.
• Chertoff, A. P. (2018). Perils of lethal autonomous weapons systems proliferation: Preventing non-state acquisition. Technical Report 2, Geneva Centre for Security Policy.
• Danzig, R. (2012). Innovation, dual use, and security: Managing the risks of emerging biological and chemical technologies. MIT Press.
• Das, R. K., Sammi, S. S., Kobra, K., Ajmain, M. R., Khushbu, S. A., & Noori, S. R. H. (2022). Analysis of bangla transformation of sentences using machine learning. In International conference on deep learning, artificial intelligence and robotics (pp. 36–52). Springer.
• de Graaf, R., & van der Vossen, R. (2013). Bits versus brains in content analysis. Comparing the advantages and disadvantages of manual and automated methods for content analysis. Communications, 38(4), 433–443. https://doi.org/10.1515/commun-2013-0025
• European Commission. (2023). EU dual-use regulation. https://eur-lex.europa.eu/legal-content/en/txt/?uri=celex%3a32009r0428
• Forge, J. (2010). A note on the definition of 'dual use'. Science and Engineering Ethics, 16(1), 111–118. https://doi.org/10.1007/s11948-009-9159-9
• Gigi Kwik, M. Z., Haider, S. A., & Hameed, A. (2022). H5N1: A case study for dual-use research discusses the controversy surrounding the gain-of-function research on the H5N1 virus [Unpublished manuscript/Working paper].
• Grinbaum, A. (2017). The dual-use dilemma: Ethical considerations and policy frameworks for research with biosecurity implications. Springer.
• Guillemin, J. (2005). Biological weapons: From the invention of state-sponsored programs to contemporary bioterrorism. Columbia University Press.
• Helm, J. M., Swiergosz, A. M., Haeberle, H. S., Karnuta, J. M., Schaffer, J. L., Krebs, V. E., & Ramkumar, P. N. (2020). Machine learning and artificial intelligence: Definitions, applications, and future directions. Current Reviews in Musculoskeletal Medicine, 13, 69–76.
• Imperiale, M. J., & Casadevall, A. (2015). A new synthesis for dual-use research of concern. PLOS Medicine, 12(4). https://doi.org/10.1371/journal.pmed.1001813
• Jaffe, A. B., Trajtenberg, M., & Henderson, R. (1993). Geographic localization of knowledge spillovers as evidenced by patent citations. Quarterly Journal of Economics, 108(3), 577–598.
• Jobin, A., Ienca, M., & Vayena, E. (2019). The ethics of artificial intelligence. Nature, 569(7753), 334–341.
• Jones, D., Gkoutos, G., Mungall, C., & Harris, M. A. (2021). Ontology best practices for knowledge graphs. Journal of Biomedical Semantics, 12(1), 8.
• Lu, Z., Zhu, Y., Pan, S., Xiang, E., Wang, Y., & Yang, Q. (2014). Source-free transfer learning for text classification. In Proceedings of the AAAI conference on artificial intelligence (Vol. 28).
• Matthes, J., & Kohring, M. (2008). The content analysis of media frames: Toward improving reliability and validity. Journal of Communication, 58(2), 258–279.
• Meyer, M. A., & Booker, J. M. (2001). Eliciting and analyzing expert judgment. SIAM Publications.
• Naseri, M., Baraldi, P., Compare, M., & Zio, E. (2016). Availability assessment of oil and gas processing plants operating under dynamic arctic weather conditions. Reliability Engineering & System Safety, 152, 66–82.
• National Institutes of Health (NIH). (2023). Dual use research of concern. https://oir.nih.gov/sourcebook/ethical-conduct/special-research-considerations/dual-use-research
• O'Neil, C. (2017). Weapons of math destruction: How big data increases inequality and oversight of dual use life sciences research.
• Qasim, M., Salman, M., Pedersen, J. M., Masood, A., & Abbas, H. (2024). NLP and ML synergy: A novel approach in botnet detection from sandbox artifacts. In 2024 ASU international conference in emerging technologies for sustainability and intelligent systems (ICETSIS) (pp. 1679–1684). IEEE.
• Rutger, D., & Robert, V. (2013). Bits versus brains in content analysis. Communications, 38(4), 433–443.
• Seager, T., Lambert, J., & Gardner, K. (2007). Fostering innovation in contaminated sediments management through multicriteria technology assessment and public participation. Risk Analysis: An International Journal, 27(4), 1043–1052.
• Smorodinskaya, N., Russell, M., Katukov, D., & Still, K. (2017). Innovation ecosystems vs. innovation systems in terms of collaboration and co-creation of value.
• Straus, D. (2002). How to make collaboration work: Powerful ways to build consensus, solve problems, and make decisions. Berrett-Koehler Publishers.
• Supriyono, Wibawa, A. P., Suyono, & Kurniawan, F. (2024). Advancements in natural language processing: Implications, challenges, and future directions. Telematics and Informatics Reports, 16, 100173. https://doi.org/10.1016/j.teler.2024.100173
• Tapscott, D., & Williams, A. D. (2008). Wikinomics: How mass collaboration changes everything. Penguin.
• USAID. (2023). Cybersecurity agriculture and food security: Why does cybersecurity matter for agriculture and food security? [Technical report]. United States Agency for International Development. https://www.usaid.gov/sites/default/files/2023-10/Cybersecurity%20briefer_Agriculture%20and%20food%20security.Pdf
• Weber, M. (2017). Comment on 'does your surname affect the citability of your publications'. Journal of Informetrics, 11(3), 835–837.
• Yassif, J. M. (2022). Preventing catastrophic bioterrorism: Guarding against exploitation of the life sciences and biotechnology. CTC Sentinel, 15(7), 27–31.
• Zhou, N., Zhang, Z., Nair, V. N., Singhal, H., & Chen, J. (2022). Bias, fairness and accountability with artificial intelligence and machine learning algorithms. International Statistical Review, 90(3), 468–480.