# Detecting Rug Pulls in Decentralized Exchanges: Machine Learning Evidence from the TON Blockchain

arXiv: https://arxiv.org/abs/2509.01168 · HTML: https://mlsanity.com/paper/2509.01168/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Empirical Review of Automated Analysis Tools on 47,587 Ethereum Smart Contracts](https://mlsanity.com/paper/1910.10601/) (2019)
- [An Overview on Smart Contracts: Challenges, Advances and Platforms](https://mlsanity.com/paper/1912.10370/) (2019)
- [Token Spammers, Rug Pulls, and SniperBots: An Analysis of the Ecosystem of Tokens in Ethereum and in the Binance Smart Chain (BNB)](https://mlsanity.com/paper/2206.08202/) (2022)
- [Dual-channel Early Warning Framework for Ethereum Ponzi Schemes](https://mlsanity.com/paper/2206.07895/) (2022)
- [Evolve Path Tracer: Early Detection of Malicious Addresses in Cryptocurrency](https://mlsanity.com/paper/2301.05412/) (2023)
- [SoK: Comprehensive Analysis of Rug Pull Causes, Datasets, and Detection Tools in DeFi](https://mlsanity.com/paper/2403.16082/) (2024)
- [The Kosmosis Approach to Crypto Rug Pull Detection](https://mlsanity.com/paper/2405.19762/) (2024)

## Built on by (most cited first, 2 of 2)

- [MELT: A Behavioral Trace Dataset for High-Risk Memecoin Launch Detection](https://mlsanity.com/paper/2602.13480/) (2026)
- [Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning](https://mlsanity.com/paper/2608.20271/) (2026)

## Abstract (arXiv)

This paper presents a machine learning framework for the early detection of rug pull scams on decentralized exchanges (DEXs) within The Open Network (TON) blockchain. TON's unique architecture, characterized by asynchronous execution and a massive web2 user base from Telegram, presents a novel and critical environment for fraud analysis. We conduct a comprehensive study on the two largest TON DEXs, Ston.Fi and DeDust, fusing data from both platforms to train our models. A key contribution is the implementation and comparative analysis of two distinct rug pull definitions--TVL-based (a catastrophic liquidity withdrawal) and idle-based (a sudden cessation of all trading activity)--within a single, unified study. We demonstrate that Gradient Boosting models can effectively identify rug pulls within the first five minutes of trading, with the TVL-based method achieving superior AUC (up to 0.891) while the idle-based method excels at recall. Our analysis reveals that while feature sets are consistent across exchanges, their underlying distributions differ significantly, challenging straightforward data fusion and highlighting the need for robust, platform-aware models. This work provides a crucial early-warning mechanism for investors and enhances the security infrastructure of the rapidly growing TON DeFi ecosystem.