Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The Kosmosis Use-Case of Crypto Rug Pull Detection and Prevention

Philipp Stangl, Christoph P. Neumann

TL;DR

The paper addresses the limitations of transaction-graphbased rug-pull detection by proposing Kosmosis, an incremental knowledge-graph construction pipeline that fuses Ethereum blockchain data with social media to capture transaction semantics. It introduces an ETHOn-based ontology and modules for ABI decoding, address relation extraction, tagging, and entity resolution, integrated with text enrichment and external knowledge sources. Through a real-world 2021 rug-pull use case (e.g., Homer_eth), it demonstrates semantic querying and potential preventive alerts prior to user interactions. The approach offers a practical, extensible framework for fraud prevention in crypto ecosystems, with plans to generalize to more data sources and blockchains and to implement real-time alerting.

Abstract

Current methods to prevent crypto asset fraud are based on the analysis of transaction graphs within blockchain networks. While effective for identifying transaction patterns indicative of fraud, it does not capture the semantics of transactions and is constrained to blockchain data. Consequently, preventive methods based on transaction graphs are inherently limited. In response to these limitations, we propose the Kosmosis approach, which aims to incrementally construct a knowledge graph as new blockchain and social media data become available. During construction, it aims to extract the semantics of transactions and connect blockchain addresses to their real-world entities by fusing blockchain and social media data in a knowledge graph. This enables novel preventive methods against rug pulls as a form of crypto asset fraud. To demonstrate the effectiveness and practical applicability of the Kosmosis approach, we examine a series of real-world rug pulls from 2021. Through this case, we illustrate how Kosmosis can aid in identifying and preventing such fraudulent activities by leveraging the insights from the constructed knowledge graph.

The Kosmosis Use-Case of Crypto Rug Pull Detection and Prevention

TL;DR

The paper addresses the limitations of transaction-graphbased rug-pull detection by proposing Kosmosis, an incremental knowledge-graph construction pipeline that fuses Ethereum blockchain data with social media to capture transaction semantics. It introduces an ETHOn-based ontology and modules for ABI decoding, address relation extraction, tagging, and entity resolution, integrated with text enrichment and external knowledge sources. Through a real-world 2021 rug-pull use case (e.g., Homer_eth), it demonstrates semantic querying and potential preventive alerts prior to user interactions. The approach offers a practical, extensible framework for fraud prevention in crypto ecosystems, with plans to generalize to more data sources and blockchains and to implement real-time alerting.

Abstract

Current methods to prevent crypto asset fraud are based on the analysis of transaction graphs within blockchain networks. While effective for identifying transaction patterns indicative of fraud, it does not capture the semantics of transactions and is constrained to blockchain data. Consequently, preventive methods based on transaction graphs are inherently limited. In response to these limitations, we propose the Kosmosis approach, which aims to incrementally construct a knowledge graph as new blockchain and social media data become available. During construction, it aims to extract the semantics of transactions and connect blockchain addresses to their real-world entities by fusing blockchain and social media data in a knowledge graph. This enables novel preventive methods against rug pulls as a form of crypto asset fraud. To demonstrate the effectiveness and practical applicability of the Kosmosis approach, we examine a series of real-world rug pulls from 2021. Through this case, we illustrate how Kosmosis can aid in identifying and preventing such fraudulent activities by leveraging the insights from the constructed knowledge graph.
Paper Structure (24 sections, 5 figures, 1 table)

This paper contains 24 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Kosmosis Objectives
  3. Background
  4. The Ethereum Blockchain
  5. Blockchain Data Structure
  6. Smart Contracts
  7. Externally Owned Account
  8. Account-based Accounting
  9. Token Minting
  10. Rug Pull Detection Methods
  11. The Kosmosis Approach to Incremental Knowledge Graph Construction
  12. Blockchain Data Processing
  13. Address Relation Extraction
  14. Address Tagging
  15. Blockchain Entity Resolution
  16. ...and 9 more sections

Figures (5)

  • Figure 1: Schematic representation of deploying and reading from smart contracts. Adapted from eiki2023.
  • Figure 2: A high level overview of the Kosmosis pipeline.
  • Figure 3: Simplified transaction graph of Homer_eth's nft rug pulls.
  • Figure 4: Knowledge graph of Homer_eth's nft rug pulls, constructed using Kosmosis.
  • Figure 5: Token and nft rug pulls and scams since 2017. (a) depicts the number of rug pull and scams by month and year since 2017, highlighting a far great number of rug pulls compared to scam, (b) shows the amount stolen at time of rug pull with a peak in 2021, and (c) shows the number of rug pulls per year with a sharp rise in 2021. Adapted from comparitech2023.