# BlockScan: Detecting Anomalies in Blockchain Transactions

arXiv: https://arxiv.org/abs/2410.04039 · HTML: https://mlsanity.com/paper/2410.04039/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)
- [Learning and Evaluating Representations for Deep One-class Classification](https://mlsanity.com/paper/2011.02578/) (2020)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [A Review on Graph Neural Network Methods in Financial Applications](https://mlsanity.com/paper/2111.15367/) (2021)
- [When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?](https://mlsanity.com/paper/2309.05520/) (2023)
- [Top Score on the Wrong Exam: On Benchmarking in Machine Learning for Vulnerability Detection](https://mlsanity.com/paper/2408.12986/) (2024)
- [BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection](https://mlsanity.com/paper/2303.18138/) (2023)
- [Blockchain Large Language Models](https://mlsanity.com/paper/2304.12749/) (2023)
- [Anomaly Detection in Blockchain Networks: A Comprehensive Survey](https://mlsanity.com/paper/2112.06089/) (2021)
- [SoK: Transparent Dishonesty: front-running attacks on Blockchain](https://mlsanity.com/paper/1902.05164/) (2019)
- [Detecting Anomalies in Blockchain Transactions using Machine Learning Classifiers and Explainability Analysis](https://mlsanity.com/paper/2401.03530/) (2024)

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

- [Blockchain Data Analysis in the Era of Large-Language Models](https://mlsanity.com/paper/2412.09640/) (2024)
- [Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions](https://mlsanity.com/paper/2510.20102/) (2025)

## Abstract (arXiv)

We propose BlockScan, a customized Transformer for anomaly detection in blockchain transactions. Unlike existing methods that rely on rule-based systems or directly apply off-the-shelf large language models (LLMs), BlockScan introduces a series of customized designs to effectively model the unique data structure of blockchain transactions. First, a blockchain transaction is multi-modal, containing blockchain-specific tokens, texts, and numbers. We design a novel modularized tokenizer to handle these multi-modal inputs, balancing the information across different modalities. Second, we design a customized masked language modeling mechanism for pretraining the Transformer architecture, incorporating RoPE embedding and FlashAttention for handling longer sequences. Finally, we design a novel anomaly detection method based on the model outputs. We further provide theoretical analysis for the detection method of our system. Extensive evaluations on Ethereum and Solana transactions demonstrate BlockScan's exceptional capability in anomaly detection while maintaining a low false positive rate. Remarkably, BlockScan is the only method that successfully detects anomalous transactions on Solana with high accuracy, whereas all other approaches achieved very low or zero detection recall scores. This work sets a new benchmark for applying Transformer-based approaches in blockchain data analysis.