arXiv:2607. 19350v1 Announce Type: new Abstract: Financial institutions face significant challenges in detecting sophisticated money laundering patterns, such as smurfing and layering, due to extreme data imbalance (0.
arXiv:2607. 04184v1 Announce Type: new Abstract: Market manipulation is the dubious practice of manipulating stock prices in order to make a quick profit, which truly degrades confidence on trading platforms.
arXiv:2607. 09704v1 Announce Type: new Abstract: We present an exploratory benchmark and quantum-inspired modeling prototype for fraud screening in dynamic financial transaction graphs.
The paper presents a semi‑supervised learning framework for detecting illicit Bitcoin flows in Shared Send Mixers, using a large historical dataset of 163 million transactions. It demonstrates that the success of SSL depends on data quality rather than sheer volume, with high‑fidelity features such as KeyLinker address clustering and Shared Send Untangling complexity metrics achieving an F1 score of 0.84 on unlabeled data. The study also shows that common heuristics like One‑Time Change introduce noise, underscoring the importance of smarter feature engineering in blockchain forensics.
Bitcoin's pseudonymous nature makes it challenging to analyze user-level activity, since a single user may control multiple identifiers (addresses). Existing heuristic-based methods attempt to identif...
The paper introduces a method to improve heuristic-based Bitcoin address clustering by using graph neural networks to generate contrastive embeddings. It releases a large Bitcoin transaction graph dataset, presents a learning framework that aligns embeddings with existing heuristics, and applies hierarchical clustering to refine clusters and detect suspicious merges. The approach offers a more modular and theoretically grounded way to analyze user-level activity on the blockchain.
The paper introduces Temporal-Context Edge Enrichment (TCEE), a framework that uses frozen time‑series foundation models (TSFMs) to summarise each account’s transaction history and enrich transaction representations with temporal context. These enriched edges can be directly scored for classification or used as features in a graph neural network (GNN). Across six AMLWorld datasets, TCEE improves PR‑AUC by an average of 10.8% over the best baseline and trains 6.0× faster; when combined with a GNN, it yields an additional 4.8% improvement on smaller datasets and a 14.5% gain on an Ethereum phishing dataset.
The paper introduces Centroid‑Guided Contrastive Loss (CGCL), a novel loss function that combines classification with dense clustering to improve fraudulent job posting detection. CGCL reshapes the latent space using a centroid‑driven top‑k push‑and‑pull mechanism, ensuring accurate decision boundaries while preserving compact clustering of similar fake posts. Experiments on the EMSCAD benchmark show that CGCL achieves state‑of‑the‑art performance.
Evi-VN is a new framework for graph neural network (GNN) fraud detection that injects evidence from diverse modalities—structured records, text, images, and audio—into virtual node representations. It targets shared hard regions where standard GNNs fail to distinguish well‑disguised fraudsters from legitimate users, correcting blind spots without disrupting reliable predictions. Experiments on bot, fake‑review, refund‑evidence, and telecom‑fraud datasets demonstrate its effectiveness across generic, fraud‑specific, and unseen GNNs.
arXiv:2609.13499v1 Announce Type: cross Abstract: Private Evolution (PE) generates high-fidelity synthetic data in federated settings without exposing users' raw data. It aggregates clipped user vote...
The paper introduces GARG-AML, a graph-based framework designed to detect smurfing—a money‑laundering technique that splits large transactions into smaller ones—to improve anti‑money laundering efforts. It quantifies smurfing risk with a single interpretable metric derived from the second‑order transaction network, offering a balance between computational efficiency and transparency. The authors demonstrate GARG‑AML’s scalability on large random networks and its effectiveness on two open‑source money‑laundering datasets, suggesting it can enhance smurfing detection and support investigative decision‑making.
The paper introduces CATeye, a Coupled Attribute-Topology Invariance Learning framework designed to detect voucher abuse in e-commerce. It addresses coupled attribute-topology shifts by employing an Attribute Invariance Selector to mask non-invariant attributes and an Edge Invariance Selector to sample invariant subgraphs, thereby creating multiple views that emphasize domain-invariant representations. Experiments on a Lazada dataset and a public benchmark demonstrate that CATeye outperforms nine baseline methods, achieving up to an 8.61% improvement in average F1 score.