Graphlet-based Decentralized Finance Transaction Method Classification

Célestin Coquidé; Alessio Brini; Natkamon Tovanich

Home/Archive/arXiv

arXiv · 2610.23466

Graphlet-based Decentralized Finance Transaction Method Classification

Célestin Coquidé·Alessio Brini·Natkamon Tovanich

View original source ↗Read source document ↗Export metadata ↓

Abstract

Decentralized Finance (DeFi) transactions involve complex interactions among accounts, smart contracts, and tokens. We investigate whether network topology can identify transaction methods that describe DeFi operations. We extract directed graphlet features to classify the 30 most frequent methods. Our results show that graphlet features complement event log counts in improving classification performance. Using SHapley Additive exPlanations (SHAP), we further derive model explanations that reveal method-specific graphlet structural patterns.

Explore related subjects

cs.SI cs.CE cs.CY cs.ET cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Célestin Coquidé, Alessio Brini, Natkamon Tovanich. 2026-10-16. Graphlet-based Decentralized Finance Transaction Method Classification. https://arxiv.org/abs/2610.23466

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering

Money laundering, a global problem estimated to account for 2%-5% of the global GDP, required regulators to enforce stringent rules on financial institutions to combat it. One prominent laundering method, called smurfing, relies on breaking up transactions into smaller amounts to evade detection. Given the complexity of laundering schemes, involving numerous transactions across multiple parties, network analytics is an important tool for anti-money laundering. However, recent advances in network analytics have leaned heavily on black-box network embedding methods, limiting their utility in businesses. To address the specific nature of smurfing and banks' operational requirements, this paper introduces GARG-AML, a novel graph-based method that quantifies smurfing risk through a single interpretable metric derived from the structure of the second-order transaction network. Unlike traditional methods, GARG-AML provides a balance between computational efficiency and transparency, enabling integration into existing AML workflows. We demonstrate the scalability of GARG-AML on large random networks, and its performance on two open-source money laundering datasets. Our results highlight the potential of GARG-AML to enhance smurfing detection and support investigative decision-making.

cs.SI↗

arXiv2026

A null model to detect coordinated online behavior integrating evidence from multiple indicators

Coordinated online accounts can amplify messages and manipulate attention, but detecting such behavior is challenging due to confounding factors like account activity and item popularity. We propose a statistical null-model framework that assesses behavioral similarity between accounts by comparing observed coordination indicators against activity- and popularity-conditioned reference distributions. By combining evidence across multiple indicators and partners, our method can identify suspicious coordination links more accurately. Evaluations on nine labeled information-operation datasets involving over 152 thousand accounts show that aggregating p-values multiplicatively across indicators and partners yields improved detection performance. While results vary across information operations, this approach offers a generalizable and statistically principled tool for uncovering coordinated online behavior.

cs.SI↗

arXiv2026

Validating LLM-generated political networks with survey-reported partisan exposure

Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. However, in network formation tasks, existing evaluations often focus on aggregate network properties, while networks with plausible structural properties may still fail to reproduce individuals' social and political environments. Here, we generate LLM-based political networks using personas sampled from the nationally representative ANES 2020--2022 Social Media Study and use respondents' survey-reported partisan exposure as an empirical benchmark for the political environments generated for the corresponding personas. We first characterize the structural properties and political assortativity of the generated networks, and then compare ego-level partisan exposure with the survey. We find that the structure and political assortativity of the generated networks vary across experimental configurations. More importantly, when comparing generated partisan exposure with the survey, some models generate stronger separation between Democratic and Republican egos than reported in the survey, with higher same-party and lower cross-party exposure, while others mainly underestimate Republican exposure across ego groups. Moreover, networks with similar political assortativity can still generate different partisan environments around the same personas, including among networks with plausible structural properties. Finally, generated networks show group-specific errors, under- or overestimating exposure to either Democrats or Republicans for specific social groups. These findings show that evaluating LLM-based social simulations only through aggregate outcomes can hide errors in the local environments through which those outcomes emerge, highlighting the importance of validation at both aggregate and individual levels.

cs.SI↗