Cryptocurrency users increasingly rely on obfuscation techniques such as mixers, swappers, and decentralised or no-KYC exchanges to protect their anonymity. However, at the same time, these services are exploited by criminals to conceal and launder illicit funds. Among obfuscation services, mixers remain one of the most challenging entities to tackle. This is because their owners are often unwilling to cooperate with Law Enforcement Agencies, and technically, they operate as ‘black boxes’. To better understand their functionalities, this paper proposes an approach to analyse the operations of mixers by examining their address-transaction graphs and identifying topological similarities to uncover common patterns that can define the mixer’s modus operandi. The approach utilises community detection algorithms to extract dense topological structures and clustering algorithms to group similar communities. The analysis is further enriched by incorporating data from external sources related to known Exchanges, in order to understand their role in mixer operations. The approach is applied to dissect the Blender.io mixer activities within the Bitcoin blockchain, revealing: i) consistent structural patterns across address-transaction graphs; ii) that Exchanges play a key role, following a well-established pattern, which raises several concerns about their AML/KYC policies. This paper represents an initial step toward dissecting and understanding the complex nature of mixer operations in cryptocurrency networks and extracting its modus operandi.

Abstract Classification of Bitcoin entities is an important task to help Law Enforcement Agencies reduce anonymity in the Bitcoin blockchain network and to detect classes more tied to illegal activities. However, this task is strongly conditioned by a severe class imbalance in Bitcoin datasets. Existing approaches for addressing the class imbalance problem can be improved considering generative adversarial networks (GANs) that can boost data diversity. However, GANs are mainly applied in computer vision and natural language processing tasks, but not in Bitcoin entity behaviour classification where they may be useful for learning and generating synthetic behaviours. Therefore, in this work, we present a novel approach to address the class imbalance in Bitcoin entity classification by applying GANs. In particular, three GAN architectures were implemented and compared in order to find the most suitable architecture for generating Bitcoin entity behaviours. More specifically, GANs were used to address the Bitcoin imbalance problem by generating synthetic data of the less represented classes before training the final entity classifier. The results were used to evaluate the capabilities of the different GAN architectures in terms of training time, performance, repeatability, and computational costs. Finally, the results achieved by the proposed GAN-based resampling were compared with those obtained using five well-known data-level preprocessing techniques. Models trained with data resampled with our GAN-based approach achieved the highest accuracy improvements and were among the best in terms of precision, recall and f1-score. Together with Random Oversampling (ROS), GANs proved to be strong contenders in addressing Bitcoin class imbalance and consequently in reducing Bitcoin entity anonymity (overall and per-class classification performance). To the best of our knowledge, this is the first work to explore the advantages and limitations of GANs in generating specific Bitcoin data and “attacking” Bitcoin anonymity. The proposed methods ultimately demonstrate that in Bitcoin applications, GANs are indeed able to learn the data distribution and generate new samples starting from a very limited class representation, which leads to better detection of classes related to illegal activities.

Network traffic analysis is an important cybersecurity task, which helps to classify anomalous, potentially dangerous connections. In many cases, it is critical not only to detect individual malicious connections, but to detect which node in a network has generated malicious traffic so that appropriate actions can be taken to reduce the threat and increase the system’s cybersecurity. Instead of analysing connections only, node behavioural analysis can be performed by exploiting the graph information encoded in a connection network. Network traffic, however, is temporal data and extracting graph information without a fixed time scope may only unveil macro-dynamics that are less related to cybersecurity threats. To address these issues, a threefold approach is proposed here: firstly, temporal dissection for extracting graph-based information is applied. As the resulting graphs are typically affected by class imbalance (i.e. malicious nodes are under-represented), two novel graph data-level preprocessing techniques - R-hybrid and SM-hybrid - are introduced, which focus on exploiting the most relevant graph substructures. Finally, a Neural Network (NN) and two Graph Convolutional Network (GCN) approaches are compared when performing node behaviour classification. Furthermore, we compare the node classification performance of these supervised models with traditional unsupervised anomaly detection techniques. Results show that temporal dissection parameters affected classification performance, while the data-level preprocessing strategies reduced class imbalance and led to improved supervised node behaviour classification, outperforming anomaly detection models. In particular, Neural Network (NN) outperformed Graph Convolutional Network (GCN) approaches for two attack families and was less affected by class imbalance, yet one GCN performed best overall. The presented study successfully applies a temporal graph-based approach for malicious actor detection in network traffic data.

In this paper we present a method for constructing a special case of interval type 2 fuzzy sets from a grayscale image. We use properties that are exclusive of these sets in order to represent the changes in intensity in the image and so create what in image processing is known as false edges.