Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This removes both the overnight batch window in which anti-m...
FinalityBench is an executable benchmark that tests how agents decide on shipping, re‑capturing, refunding, or waiting when a merchant’s payment processor, ledger, ERP, and bank feed receive delayed, duplicated, dropped, or reordered messages, causing contradictory beliefs about an order. The benchmark uses a hidden canonical event log and faulted delivery streams to generate system views, scoring each episode by the merchant’s terminal economic position relative to a privileged reference. It contains 321 tasks, including 45 twin pairs where all four views are identical yet the correct disposition differs, and evaluates nine programmatic policies, revealing that a ship‑on‑first‑sign policy performs best by accuracy but worst by paired loss, while a runtime‑gated irreversible‑action policy achieves 85.4% accuracy without losing money.
The paper presents a graph‑based method for detecting money‑mule accounts by treating a bank’s relational schema as a heterogeneous graph and scoring each account using multi‑hop neighbourhoods, per‑column encoders, relative‑time encoding, and HeteroGraphSAGE message passing. On a five‑year RBIH retail‑banking dataset of 400 million transactions, the model achieves 83 % precision and a 0.5 % false‑alarm rate, recovering nine out of ten held‑out mules and outperforming tree‑based baselines in recall while maintaining precision deep into the alert queue. The approach can be deployed directly on a bank’s existing database without constructing a custom feature graph.
Money-mule networks move criminal funds through many small transfers, each of which looks ordinary on its own. What marks an account as a mule lies outside any single transfer: in the counterparties a...
arXiv:2604. 17420v2 Announce Type: replace-cross Abstract: Money laundering poses severe risks to global financial systems, driving the widespread adoption of machine learning for transaction monitoring.
arXiv:2602. 03981v2 Announce Type: replace-cross Abstract: Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies.
arXiv:2608. 02664v1 Announce Type: cross Abstract: Deploying ML models in regulated decision-making (credit underwriting, fraud detection, loan approval) requires demonstrating fairness and robustness to auditors without exposing model weights or customer data.
AMLworld-Compact introduces an importance‑weighted downsampling protocol for evaluating large language models on AMLworld’s test splits, retaining all illicit transactions while sampling benign ones from supervised‑score strata. The HT‑Coreset method reduces evaluation targets by 271× on HI‑Small and 611× on LI‑Small, providing unbiased confusion‑count estimates with exact recall and ratio estimates for precision and F1. Experiments with boosted‑tree strata and Graph Feature Preprocessor features show lower F1 RMSE compared to uniform sampling, and audit tools reveal that lexical checks do not reliably indicate correctness of model outputs.
arXiv:2609.23659v1 Announce Type: new Abstract: Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create...
The paper presents a deployed system that scores blockchain addresses using their position in a massive multi‑chain transaction graph instead of relying on sanctions lists. The system operates on a single graph of 835 million addresses and 15.8 billion edges across five EVM chains, employing a shared inductive encoder with per‑chain normalization and two scoring heads. It demonstrates label‑free transfer, achieving high recall on held‑out positives for Base, Arbitrum, and Gnosis at a very low alert rate, and shows significant lead time over external registry events, while maintaining fast, reproducible serving performance.
BENCHCOMPASS is a new payment‑domain benchmark that transforms typed evidence packs into scenario‑grounded tasks, applies LLM‑based quality checks, generates attack variants, and reserves final item admission for domain experts. It includes an expert‑reviewed Pro benchmark covering payment knowledge, context‑grounded scenario reasoning, and attacked open robustness, plus a lower‑assurance Normal pool. Across 16 model variants, BENCHCOMPASS reveals distinct failure modes—missing payment knowledge, incomplete reasoning, and failure to reject invalid workflows—while the best model scores 89.6% on open context‑grounded reasoning and 81.7% under attacked inputs. "whyItMatters":"The benchmark provides a structured way to isolate and evaluate specific weaknesses in LLMs for payment operations, a critical financial infrastructure where rules change rapidly and decisions depend on complex contextual factors."
arXiv:2607. 10131v1 Announce Type: cross Abstract: Money laundering threatens financial stability and exposes institutions to penalties, motivating automated detection.