A Primer on Security and Fraud Detection

“All warfare is based on deception.” - Sun Tzu

The history of fraud is as old as time. Fraud in the crypto world comes as no surprise, and as crypto gains mainstream adoption, it becomes increasingly necessary to be aware of the different forms of fraud in order to be able to identify it.

Fraud is a significant issue for businesses in general, for governments, and for the blockchain industry in particular. According to the 2022 PwC Global Annual Review on fraud, 46% of surveyed organizations reported experiencing some form of fraud or economic crime within the last 24 months.

Governments are aware of the issue for tax purposes, as well as to combat money laundering and terrorism financing. Relevant agencies have a mandate to enforce the law and combat such illicit activity even if cryptocurrencies are involved. Due diligence is required for all subjects associated with financial activity or money services businesses, a...

Technical requirements

You can find all the data and code files for this chapter in the book’s GitHub repository at https://github.com/PacktPublishing/Data-Science-for-Web3/tree/main/Chapter10. We recommend that you read through the code files in the Chapter10 folder to follow along.

In this chapter, we will use the Ethereum Utilities library (eth-utils), which contains commonly used utility functions for Python developers working with Ethereum. Depending on our environment, we may need to import additional low-level libraries that are utilized by eth-utils.

If you haven’t installed eth-utils yet, you can do so using the following code snippet:

pip install eth-utils

The documentation for eth-utils is available at https://eth-utils.readthedocs.io/en/stable/. If the installation fails due to a lack of supporting libraries, you can find the complete list of required libraries that need to be pre-installed in Chapter10/EDA.ipynb.

A primer on illicit activity on Ethereum

There is a technical difference between fraud and a scam. A scam is an act where we unknowingly pay for a fake item, transfer money, or provide our private keys to a criminal. Conversely, fraud refers to any suspicious activity on our address that we did not authorize. In this book, we will use both terms interchangeably.

The Ethereum Security blog has three key messages for anyone starting in the crypto industry:

• Always be skeptical
• No one is going to give you free or discounted ETH
• No one needs access to your private keys or personal information

As of today, some of the most common scams include the following:

• Giveaway scams: These basically work by criminals promising that if we send X amount of crypto to an address, it will be returned to us but doubled in amount. These schemes are often psychological, offering the victim only a limited amount of time to participate in this “opportunity,” generating...

Summary

In conclusion, we have identified and discussed one of the key threats in the cryptocurrency space, highlighting the need for effective transaction monitoring and identification. To this end, we have undertaken a machine learning exercise at the Ethereum address level, where we have leveraged Etherscan to complete our dataset.

We have evaluated and compared various machine learning models, optimizing their performance through grid search hyperparameter tuning and cross-validation. By undertaking this project, we have dived into a subject matter where forensics professionals are active and remains a current news topic.

Blockchain forensics is one of the more innovative areas in data science applications, as models need to scale and keep evolving in order to adapt, to be able to spot new types of fraud and scams.

In the next chapter, we will dive into predicting prices.

Further reading

Following is a list of sources for your further reading purposes:

• PwC. (2022). PwC’s Global Economic Crime and Fraud Survey 2022. https://www.pwc.com/gx/en/forensics/gecsm-2022/PwC-Global-Economic-Crime-and-Fraud-Survey-2022.pdf
• Furneaux, N. (2018). Investigating cryptocurrencies: Understanding, extracting, and analyzing blockchain evidence. John Wiley & Sons. Page 268.
• Sfarrugia15/Ethereum_Fraud_Detection. (n.d.). GitHub: https://github.com/sfarrugia15/Ethereum_Fraud_Detection
• Steven Farrugia, Joshua Ellul, George Azzopardi, Detection of illicit accounts over the Ethereum blockchain, Expert Systems with Applications, volume 150, 2020, 113318, ISSN 0957-4174: https://doi.org/10.1016/j.eswa.2020.113318.
• Exploiting Blockchain data to detect Smart Contract Ponzi Schemes on Ethereum. (2019, March 18). IEEE Xplore: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8668768
• Ethereum security and scam prevention. (n.d.). ethereum.org...