TY - GEN
T1 - AI-Driven Reasoning Mechanism for Enhanced Detection of Illicit Money Flows
AU - Adamyk, Bogdan
AU - Benson, Vladlena
AU - Shevchuk, Ruslan
AU - Al-Khateeb, Haider
AU - Grydzhuk, Dmytro
AU - Adamyk, Oksana
N1 - Copyright © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2025/10/9
Y1 - 2025/10/9
N2 - Law enforcement agencies face substantial difficulties tracking illicit money flow activities because these operations have become more complex and difficult to detect. Conventional detection methods often struggle to reveal advancing criminal financial networks effectively. To address this gap, this study proposes an innovative AI-driven reasoning mechanism that leverages advanced natural language processing, deep learning, machine learning, and human crowd intelligence. The suggested methodology exclusively incorporates automated reasoning capabilities with insights from expert human input, creating a forceful framework capable of discovering subtle patterns indicative of money laundering. By using innovative artificial intelligence tools and stylometric analysis, the reasoning mechanism increases the transparency, interpretability, and reliability of investigative processes. This research contributes to anti-money laundering investigations by supporting law enforcement agencies with a sophisticated analytical system that can detect complex money laundering activities while staying efficient and scalable.
AB - Law enforcement agencies face substantial difficulties tracking illicit money flow activities because these operations have become more complex and difficult to detect. Conventional detection methods often struggle to reveal advancing criminal financial networks effectively. To address this gap, this study proposes an innovative AI-driven reasoning mechanism that leverages advanced natural language processing, deep learning, machine learning, and human crowd intelligence. The suggested methodology exclusively incorporates automated reasoning capabilities with insights from expert human input, creating a forceful framework capable of discovering subtle patterns indicative of money laundering. By using innovative artificial intelligence tools and stylometric analysis, the reasoning mechanism increases the transparency, interpretability, and reliability of investigative processes. This research contributes to anti-money laundering investigations by supporting law enforcement agencies with a sophisticated analytical system that can detect complex money laundering activities while staying efficient and scalable.
KW - Deep learning
KW - Law enforcement
KW - Cognition
KW - Natural language processing
KW - Reliability
KW - Information technology
KW - Faces
UR - https://ieeexplore.ieee.org/document/11185663
UR - https://www.scopus.com/pages/publications/105019971120
U2 - 10.1109/ACIT65614.2025.11185663
DO - 10.1109/ACIT65614.2025.11185663
M3 - Conference publication
SN - 9798331595432
T3 - Proceedings from the International Conference on Advanced Computer Information Technologies (ACIT)
SP - 796
EP - 801
BT - 2025 15th International Conference on Advanced Computer Information Technologies (ACIT)
PB - IEEE
T2 - 2025 15th International Conference on Advanced Computer Information Technologies (ACIT)
Y2 - 17 September 2025 through 19 September 2025
ER -