The Role of AI: from Conventional Methods to Digital Crime Analysis

  • Authors

    • Lucy Tatiana Polanco Aya Luis Amigo Catholic University
    • Orlando Carmelo Castellanos Polo Luis Amigo Catholic University
    • Sol Beatriz Vélez Escobar Luis Amigo Catholic University
    • Oscar Tarrillo Saldaña National University of Trujillo
    • Luis Alexander Barboza Tarrillo National Autonomous University of Chota
    • María Esther León Morales National University of Cajamarca
    • Lennin Rodríguez Castillo National University of Cajamarca
    • Pedro Andres Valderrama Araujo Technological University of Peru
    • Carranza Guevara Rosas Toribio Rodríguez National University of Mendoza in Amazonas
    https://doi.org/10.14419/ap57rx96

    Received date: August 6, 2025

    Accepted date: September 14, 2025

    Published date: September 30, 2025

  • Artificial Intelligence, Digital Forensics, Machine Learning, Forensic Technology, and Cybersecurity Law

  • Abstract

    Current research highlights how artificial intelligence (AI) affects digital forensics, considering its development in methods, specific implementations, and repercussions on the justice system. In addition to its technical effects, emphasis is placed on its influence in reducing legal costs and improving institutional resources. According to the Europol report (2025), the processing of information in the organization of digital evidence has reduced forensic analysis time by up to 70%, representing significant savings in working hours and case backlogs (p. 4). These findings show that AI not only speeds up the identification of patterns and risks but also helps to reduce the financial burden on justice systems(Europol, 2025, March 18).

    Several studies support these findings. Fakiha (2024) indicates that an orderly and finite set of operations can reduce the time required to examine digital evidence by up to 96% (Fakiha, 2024, pp. 3-4). Furthermore, Khattak (2025) demonstrates that the accuracy of threat identification and digital evidence classification exceeds 90% (Khattak, 2025, p.112). These advances allow us to measure the economic benefits: if an analysis that previously took up to two weeks can now be completed in less than two days, the savings in expert salaries, storage costs, and legal expenses can vary between 40% and 60% (OECD, 2025, p.17).

    However, the obstacles are significant. Tageldin and Venter (2023) point out the great dangers posed by biases in algorithms and the lack of uniform regulations (p.4). In addition, there is concern about the lack of transparency in decisions that are made automatically. A recent example, reported by the Associated Press (2024), revealed how an artificial intelligence tool, which claimed to be 90% accurate, resulted in wrongful convictions in the courts due to its inability to be explained. These drawbacks make the discussion about digital transformation essential: the application of AI in the judicial sphere requires not only technical specifications but also adequate regulations, constant supervision, and sustainable development (Associated Press News, 2024).

  • References

    1. Akeiber, H. (2025). A comprehensive study of cybercrime and digital forensics through machine learning and AI. Al Rafidain Journal of Engineer-ing Sciences, 3(1), 369–395.
    2. Associated Press News. (2024). AI tool questioned after wrongful convictions in digital evidence cases. AP News. https://apnews.com/
    3. Baroto, R. U. (2024). Implementation of machine learning algorithms for digital evidence analysis using Autopsy. Asian Pacific Journal of Forensic Science and Technology, 6(1). https://www.apfjournal.or.id/index.php/apf/article/view/346.
    4. Canada., S. C. (2025). Annual report on digital evidence and AI tools in justice. Ottawa: Judicial Council. https://www.scc-csc.ca.
    5. DFPulse. (2024). The 2024 digital forensic practitioner survey. ScienceDirect.
    6. Dunsin, D. G. (2023). A comprehensive analysis of the role of artificial intelligence and machine learning in modern digital forensics and incident response. arXiv.
    7. Dunsin, D. G. (2023). A comprehensive analysis of the role of artificial intelligence and machine learning in modern digital forensics and incident response. arXiv.
    8. Europea., C. (2025). AI in justice: Governance and economic impact. Brussels: EU Publications.
    9. Europol. (2025, March 18). EU Serious and Organized Crime Threat Assessment. Report via AP.
    10. Fakiha, B. (2024). From data to evidence: AI in cyber forensic investigations. FIO Labs.
    11. Fakiha, B. (2024). Unlocking Digital Evidence: Recent Challenges and Strategies . Journal of Interner Services and Information Security (JISIS), 14(2). https://doi.org/10.58346/JISIS.2024.I2.005
    12. Fattahi, J. (2024). Machine learning and deep learning techniques used in cybersecurity and digital forensics: A review. arXiv.
    13. Institute., S. (27 de septiembre de 2024). Advanced Evidence Collection: DFIR’s 2024 Mobile and Cloud Shift. SANS Institute. https://www.sans.org/blog/advanced-evidence-collection-dfir-s-2024-mobile-and-cloud-shift/
    14. Khattak, J. A. (2025). Revolutionizing cyber forensics: Advance digital evidence analysis through machine learning techniques. Annual Methodo-logical Archive Research Review, 3(4), 146–159. https://www.researchgate.net/publication/390957291_Revolutionizing_Cyber_Forensics.
    15. Khattak, S. (2025). Machine learning applications in cybercrime detection. International Journal of Cybersecurity, 12(1), 110–125.
    16. Kitchenham, B. A. (2007). Guidelines for performing systematic literature reviews in software engineering. University of Keele & Durham Univer-sity.
    17. LegalTech., P. (2025). Economic evaluation of AI adoption in judicial systems. PwC Reports.
    18. Nayerifard, T. A. (2023). Machine learning in digital forensics: A systematic literature review. arXiv. https://arxiv.org/abs/2306.04965.
    19. OECD. (2025). Machine learning applications in cybercrime detection. International Journal of Cybersecurity, 12(1), 110–125.
    20. Service., C. P. (2008). Expert Witnesses – Scales of Guidance. https://www.cps.gov.uk/legal-guidance/costs-annex-3a.
    21. Singer, N. (2024, 15 de octubre.). This AI Tool Helped Convict People of Murder. Then Someone Took a Closer Look. WIRED. https://www.wired.com/story/cybercheck-crime-reports-prosecutions.
    22. Tageldin, A. &. (2023). Bias and governance challenges in forensic AI systems. Computers & Security, 134, 103452.
    23. Van Dijk, R. (2025). AI evidence in European courts: Lessons from Rotterdam. 16(2), 25-40.
    24. Verma, D. (2025, abril 1). Future directions and challenges for AI in digital forensics. LinkedIn. https://www.linkedin.com/pulse/future-directions-challenges-ai-digital-forensics-dharmendra-verma-xnp4c/.
    25. Widjaja, G. V. (2024). Artificial intelligence driven forensic analysis of digital images for cybersecurity investigations. International Journal of In-telligent Systems and Applications in Engineering, 12(4), 1053–1058. https://www.researchgate.net/profile/Shruti-Thakur-12/publication/382027462_International_Journal_of_INTELLIGENT_SYSTEMS_AND_APPLICATIONS_IN_ENGINEERING_Artificial_Intelligence Driven_Forensic_Analysis_of_Digital_Images_for_Cybersecurity_Investigations/li

  • Downloads

  • How to Cite

    Aya , L. T. P. ., Polo , O. C. C. ., Escobar , S. B. V. ., Saldaña , O. T. ., Tarrillo , L. A. B. ., Morales , M. E. L. ., Castillo , L. R. ., Araujo , P. A. V. ., & Rosas , C. G. . (2025). The Role of AI: from Conventional Methods to Digital Crime Analysis. International Journal of Accounting and Economics Studies, 12(5), 1201-1206. https://doi.org/10.14419/ap57rx96