SolRugDetector: Investigating Rug Pulls on Solana

2026-03-24

AI Summary

This study addresses the rampant rug pull fraud on Solana, exacerbated by low barriers to token creation and the absence of systematic analysis or effective detection mechanisms. It presents the first comprehensive characterization of rug pull operations and their ecosystem, uncovering novel traits such as short lifespans, price-driven dynamics, and high levels of organization. The authors introduce a manually annotated dataset comprising 117 rug pull tokens and propose SolRugDetector—a detection system that leverages on-chain transaction and state data without requiring smart contract audits. Integrating empirical analysis with machine learning, SolRugDetector outperforms existing tools on the labeled dataset. Applied to 100,063 newly launched tokens in the first half of 2025, it identified 76,469 rug pulls, demonstrating its efficacy and practical utility.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Solana has experienced rapid growth due to its high performance and low transaction costs, but the extremely low barrier to token issuance has also led to widespread Rug Pulls. Unlike Ethereum-based Rug Pulls that rely on malicious smart contracts, the unified SPL Token program on Solana shifts fraudulent behaviors toward on-chain operations such as market manipulation. However, existing research has not yet conducted a systematic analysis of these specific Rug Pull patterns on Solana. In this paper, we present a comprehensive empirical study of Rug Pulls on Solana. Based on 68 real-world incident reports, we construct and release a manually labeled dataset containing 117 confirmed Rug Pull tokens and characterize the workflow of Rug Pulls on Solana. Building on this analysis, we propose SolRugDetector, a detection system that identifies fraudulent tokens solely using on-chain transaction and state data. Experimental results show that SolRugDetector outperforms existing tools on the labeled dataset. We further conduct a large-scale measurement on 100,063 tokens newly issued in the first half of 2025 and identify 76,469 Rug Pull tokens. After validating the in-the-wild detection results, we release this dataset and analyze the Rug Pull ecosystem on Solana. Our analysis reveals that Rug Pulls on Solana exhibit extremely short lifecycles, strong price-driven dynamics, severe economic losses, and highly organized group behaviors. These findings provide insights into the Solana Rug Pull landscape and support the development of effective on-chain defense mechanisms.

Problem

• Rug Pull
• Solana
• SPL Token
• on-chain fraud
• token scam

Innovation

• Rug Pull detection
• Solana blockchain
• on-chain analysis
• fraudulent token identification
• SPL Token