Human and Social Capital Strategies for Mafia Network Disruption

Ficara, Annamaria; Curreri, Francesco; Fiumara, Giacomo; Meo, Pasquale De

doi:10.1109/tifs.2023.3256706

Cited by 12 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional attack strategies could also be implemented and tested, mainly based on community identification analysis to extend the disruption analysis beyond the use of centralities [62]. Depending on the data available, attacks based on human capital (i.e., the specific skills each individual offers in the network) can also be implemented [6,25,63]. The combination of centrality-based attacks with attacks targeting human capital can be useful for designing more sophisticated disruption strategies.…”

Section: Future Workmentioning

confidence: 99%

Directed Criminal Networks: Temporal Analysis and Disruption

Anastasiadis,

Antoniou

2024

Information

View full text Add to dashboard Cite

We extend network analysis to directed criminal networks in the context of asymmetric links. We computed selected centralities, centralizations and the assortativity of a drug trafficking network with 110 nodes and 295 edges. We also monitored the centralizations of eleven temporal networks corresponding to successive stages of investigation during the period 1994–1996. All indices reach local extrema at the stage of highest activity, extending previous results to directed networks. The sharpest changes (90%) are observed for betweenness and in-degree centralization. A notable difference between entropies is observed: the in-degree entropy reaches a global minimum at month 12, while the out-degree entropy reaches a global maximum. This confirms that at the stage of highest activity, incoming instructions are precise and focused, while outgoing instructions are diversified. These findings are expected to be useful for alerting the authorities to increasing criminal activity. The disruption simulations on the time-averaged network extend previous results on undirected networks to directed networks.

show abstract

Section: Future Workmentioning

confidence: 99%

Directed Criminal Networks: Temporal Analysis and Disruption

Anastasiadis,

Antoniou

2024

Information

View full text Add to dashboard Cite

show abstract

“…In addition, there are many machine learning tasks on graphs other than vertex classification, and work has been done on, for example, edge classification in an adversarial context (Yu et al 2018). Finally, altering a network by removing edges or nodes has been studied well beyond the context of machine learning, focusing on altering shortest paths (Miller et al 2023) or disconnecting the graph (Albert et al 2000), where there has been recent work showing the impact of selecting nodes with particular features for removal (Ficara et al 2023).…”

Section: Related Workmentioning

confidence: 99%

Complex network effects on the robustness of graph convolutional networks

Miller,

Chan,

Eliassi-Rad

2024

Appl Netw Sci

View full text Add to dashboard Cite

Vertex classification using graph convolutional networks is susceptible to targeted poisoning attacks, in which both graph structure and node attributes can be changed in an attempt to misclassify a target node. This vulnerability decreases users' confidence in the learning method and can prevent adoption in high-stakes contexts. Defenses have been proposed, focused on filtering edges before creating the model or aggregating information from neighbors more robustly. This paper considers an alternative: we investigate the ability to exploit network phenomena in the training data selection process to improve classifier robustness. We propose two alternative methods of selecting training data: (1) to select the highest-degree nodes and (2) to select nodes with many connections to the test data. In four real datasets, we show that changing the training set often results in far more perturbations required for a successful attack on the graph structure; often a factor of 2 over the random training baseline. We also run a simulation study in which we demonstrate conditions under which the proposed methods outperform random selection, finding that they improve performance most when homophily is higher, clustering coefficient is higher, node degrees are more homogeneous, and attributes are less informative. In addition, we show that the methods are effective when applied to adaptive attacks, alleviating concerns about generalizability.

show abstract

“…We also performed a study [159] applying a mixed approach on two Mafia networks, removing actors according to the maximal degree, betweenness, closeness, as well as according to special skills or knowledge. To this end, a labeled graph was built, where each node possessed a specific role according to the judicial documents of an anti-mafia operation called Montagna.…”

Section: The Mixed Approachmentioning

confidence: 99%

Covert Network Construction, Disruption, and Resilience: A Survey

et al. 2022

View full text Add to dashboard Cite

Covert networks refer to criminal organizations that operate outside the boundaries of the law; they can be mainly classified as terrorist networks and criminal networks. We consider how Social Network Analysis (SNA) is used to analyze such networks in order to attain a greater knowledge of criminal behavior. In fact, SNA allows examining the network structure and functioning by computing relevant metrics and parameters to identify roles, positions, features, and other network functioning that are not otherwise easily discovered at first glance. This is why Law Enforcement Agencies (LEAs) are showing growing interest in SNA, which is also used to identify weak spots and disrupt criminal groups. This paper provides a literature review and a classification of methods and real-case applications of disruption techniques. It considers covert network adaptability to such dismantling attempts, herein referred to as resilience. Critical problems of SNA in criminal studies are discussed, including data collection techniques and the inevitable incompleteness and biases of real-world datasets, with the aim of promoting a new research stream for both dismantling techniques and data collection issues.

show abstract

Human and Social Capital Strategies for Mafia Network Disruption

Cited by 12 publications

References 42 publications

Directed Criminal Networks: Temporal Analysis and Disruption

Directed Criminal Networks: Temporal Analysis and Disruption

Complex network effects on the robustness of graph convolutional networks

Covert Network Construction, Disruption, and Resilience: A Survey

Contact Info

Product

Resources

About