Qianyu Wang

Dr. Qianyu Wang

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 September 2024 in IEEE Network
Verified
Journal Article
Closed access
QWQianyu Wang
Qianyu Wang
WTWei-Tek Tsai
Wei-Tek Tsai
TSTianyu Shi
Tianyu Shi
In recent years, the decentralization, anonymity, and cross-border capabilities of cryptocurrencies have significantly increased their use in money laundering activities. In an era rigorously regulated by enhanced global anti-money laundering (AML) measures, designing an efficient approach to detect potential money laundering in blockchain is essential. In this research, we present GraphALM, an active learning model based on reinforcement learning, aiming to improve the detection performance of money laundering activities in blockchain transactions. This model addresses the challenge of efficiently sampling training data batches to identify illicit activities within the vast and complex dataset of Bitcoin transactions. Additionally, we have constructed a new Realistic and Demand (RD) Bitcoin dataset, augmented with feature uncertainty, to better simulate real-world scenarios. The results of our experiments demonstrate the effectiveness, robustness, and explainability of our proposed model, contributing to the application of active learning strategies in the field of financial regulation within blockchain networks.

9 November 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
QWQianyu Wang
Qianyu Wang
WTWei-Tek Tsai
Wei-Tek Tsai
BDBowen Du
Bowen Du
Given the anonymity and complexity of illegal transactions, traditional deep-learning methods struggle to establish correlations between transaction addresses, cash flows, and physical users. Additionally, the limited number of labels for illegal transactions results in severe class imbalance and other challenges. To overcome these limitations, we propose a reinforcement learning-enhanced, multi-relational, attention graph-aware framework to detect anti-money laundering and illegal trading activities. On the one hand, a data-driven, graph-aware layer establishes long-term dependencies and correlations between transaction graph nodes. Similarity among graph nodes divides the topological graph into three subgraphs. Learning from these subgraphs and converging nodes enriches local, global, and contextual details. Simultaneously, using repeated nodes across the subgraphs enhances interactivity between them, reduces intra-class ambiguity, and accentuates inter-class differences. On the other hand, a reinforcement learning module embedded in the graph-aware layer compensates for the missing details in node features caused by masking operations. Furthermore, the reconstructed loss function addresses significant classification inaccuracies by reducing the weight assigned to easily classified samples. Balancing these issues and individually supervising each component enables the detection framework to achieve optimal performance. The evaluation results demonstrate that our proposed model exhibits optimal detection performance and robustness, such as F1 of 93.85% and 94.39%.

6 May 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
QWQianyu Wang
Qianyu Wang
WTWei-Tek Tsai
Wei-Tek Tsai
TSTianyu Shi
Tianyu Shi
WTWang Tang
Wang Tang
BDBowen Du
Bowen Du
Detecting money laundering within financial networks presents a complex challenge due to the elusive behavior patterns of laundering agents, often resulting in data gaps. In this research, we propose a ‘Multiverse Simulation’ framework using a multi-agent system to generate synthetic datasets for anti-money laundering (AML) training and detection. This framework creates diverse virtual worlds, each with unique parameters to represent varying levels of illicit activity, thus mimicking the dynamics of money laundering and legitimate transactions. Our framework comprises two main types of agents: (1) the Detector, trained to identify laundering signs, and (2) Transaction agents, divided into those involved in laundering and those in legal transactions. These agents interact in a synthetic environment governed by rules that simulate real-world financial behaviors, enabling the generation of complex, realistic data. In the hide-and-seek multiverse simulation, the Detector learns to distinguish between licit and illicit transactions, a process refined by the evolving strategies of transaction agents to avoid detection. This adversarial setup fosters the co-evolution of laundering techniques and detection methods, enhancing system robustness. We demonstrate the efficacy of this approach by pre-training on synthetic cross-bank data, then evaluating with real-world data from the Elliptic dataset. Our results show that transfer learning significantly improves AML system performance, effectively bridging the gap between synthetic and authentic transaction patterns. The ‘Multiverse Simulation’ offers a scalable, dynamic approach to better understand and mitigate the gap between simulation and reality, contributing to more resilient and intelligent AML solutions.