Efficient Disruption of Criminal Networks through Multi-Objective Genetic Algorithms
Authors: Yehezkiel Darmadi, Thanh Thi Nguyen, Campbell Wilson
Organizations: Faculty of Information Technology, Monash University, Melbourne, Victoria, 3800, Australia · AiLECS Lab, Faculty of Information Technology, Monash University, Melbourne, Victoria, 3800, Australia
Criminal networks, such as the Sicilian Mafia, pose substantial threats to public safety, national security, and economic stability. Outdated disruption methods with a focus on removing influential individuals or key players have proven ineffective due to the covertness of the network. Thus, researchers have been trying to apply Social Network Analysis (SNA) techniques, such as centrality-based measures, to identify key players. However, removing individuals with high centrality often proves to be inefficient, as it does not mimic the real-world scenarios that Law Enforcement Agencies (LEAs) face. For instance, the operational costs limit the LEAs from exploiting the results of the centrality-based methods. This study proposes a multi-objective optimisation framework like the Weighted Sum Genetic Algorithm (WS-GA) and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to identify disruption strategies that balance two conflicting goals, maximising fragmentation and minimising operational cost which is captured by the spatial distance between nodes and the nearest LEA headquarters. The study utilises the "Montagna Operation" dataset for the experiments. The results demonstrate that although centrality-based approaches can fragment network effectively, they tend to incur higher operational costs. In contrast, the proposed algorithms achieve comparable disruption outcomes with significantly lower operational costs. The contribution of this work lies in incorporating operational costs in a form of spatial distance constraints into disruption strategy, which has been largely overlooked in prior studies. This research offers a scalable multi-objective capability that improves practical application of SNA in guiding LEAs in disrupting criminal networks more efficiently and strategically.
Figures & tables
Figure 1
Parameter
Values
Model
Number of Generations
500
NSGA-II and WS-GA
Population Size
500
NSGA-II and WS-GA
Number of Parents
250
NSGA-II and WS-GA
Selection Method
Tournament
NSGA-II and WS-GA
Crossover Method
Two-point method
NSGA-II and WS-GA
Mutation Method
Scramble
NSGA-II and WS-GA
TABLE I: The hyperparameters for both NSGA-II and the WS-GA
Figure 3
Fig. 5: Frequency histograms of chosen nodes in Pareto-optimal solutions for WS-GA and NSGA-II from the “Montagna Operation“ network. The y-axis shows the frequency of each node being selected in the 90 GA runs across the number of node removals. The top row displays nodes from the union of the top 10 most frequently selected, while the bottom row shows nodes from the union of the bottom 10 least frequently selected nodes by both algorithms. The left column shows the histograms constructed using the meeting dataset and the right column corresponds to phone-calls dataset.
Nodes
Role
Degree Centrality
Betweenness Centrality
47
Leader (Boss)
0.209
0.193
18
Executive Family
0.257
0.356
68
Executive Family
0.165
0.149
29
Entrepreneur
0.118
0.155
22
Pharmacist (Member)
0.112
0.080
TABLE II: Top Five Most Frequent Overlapping Nodes in WS-GA and NSGA-II in “Montagna Operation”
Metric
Real-World
WS-GA
NSGA-II
Centrality Baseline
Number of Nodes Removed
41
41
41
41
Normalised LCC ( ρ )
0.093
0.053
0.052
0.041
Spatial Distance ( D )
76.653
57.258
74.348
81.538
TABLE III: Performance comparison of LEA’s real-world arrests with competing methods
Money laundering, a global problem estimated to account for 2%-5% of the global GDP, required regulators to enforce stringent rules on financial institutions to combat it. One prominent laundering method, called smurfing, relies on breaking up transactions into smaller amounts to evade detection. Given the complexity of laundering schemes, involving numerous transactions across multiple parties, network analytics is an important tool for anti-money laundering. However, recent advances in network analytics have leaned heavily on black-box network embedding methods, limiting their utility in businesses. To address the specific nature of smurfing and banks' operational requirements, this paper introduces GARG-AML, a novel graph-based method that quantifies smurfing risk through a single interpretable metric derived from the structure of the second-order transaction network. Unlike traditional methods, GARG-AML provides a balance between computational efficiency and transparency, enabling integration into existing AML workflows. We demonstrate the scalability of GARG-AML on large random networks, and its performance on two open-source money laundering datasets. Our results highlight the potential of GARG-AML to enhance smurfing detection and support investigative decision-making.
Bruno Deprez, Bart Baesens, Tim Verdonck +1
KU Leuven · University of Antwerp - imec · University of Southampton
After the achievement of solving two-player zero-sum games, more AI researchers focus on solving multiplayer games. Urban Network Security Games (UNSGs) represent a class of such games, modeling real-world scenarios where law enforcement must strategically allocate limited resources to intercept criminals escaping within urban networks, and have gained considerable research attention. However, progress in this field has been limited by the absence of a standardized experimental platform and realistic benchmarks with heterogeneous travel costs. To address this limitation, we introduce GraphChase, an open-source platform designed to support the development and evaluation of algorithms for UNSGs. GraphChase offers a unified environment for modeling diverse UNSG variants on unweighted and weighted road networks across urban topologies. It also incorporates learning-based algorithms as baseline references for researchers. Furthermore, our experiments with GraphChase reveal that existing approaches to UNSGs still face challenges in terms of robustness and scalability, and suffer performance degradation when deployed under weighted edge costs, highlighting a sim-to-real generalization gap. GraphChase thus provides a realistic testbed for developing and validating UNSGs solvers under realistic travel-time heterogeneity.
Shuxin Zhuang, Shuxin Li, Tianji Yang +4
City University of Hong Kong CAIR, Hong Kong Institute of Science & Innovation, CAS Hong Kong, Hong Kong · Nanyang Technological University Singapore, Singapore · Georgia Institute of Technology Atlanta, Georgia, United States +2
This research investigated how online criminal activities can be better understood and connected using data-driven machine learning methods. Many illegal activities, such as human trafficking and illicit trade, have moved to online platforms where offenders hide behind anonymous accounts and frequently change identities. This makes it difficult for authorities to understand how large these networks are and how different online profiles may be linked. The research shows that people tend to maintain consistent patterns in how they write advertisements and present images online, even when they try to stay anonymous. By analysing these patterns across large collections of online advertisements, the research demonstrates how to link related accounts and identify repeated behaviour across illegal online markets. In addition, the research also addresses how such methods should be used responsibly. It proposes clear guidelines to ensure that privacy, fairness, and transparency are respected when these tools are applied. Overall, the research provides practical ways to support law enforcement investigations while emphasising careful and ethical use.