Data mining for detecting Bitcoin Ponzi schemes

نویسندگان

  • Massimo Bartoletti
  • Barbara Pes
  • Sergio Serusi
چکیده

Soon after its introduction in 2009, Bitcoin has been adopted by cyber-criminals, which rely on its pseudonymity to implement virtually untraceable scams. One of the typical scams that operate on Bitcoin are the so-called Ponzi schemes. These are fraudulent investments which repay users with the funds invested by new users that join the scheme, and implode when it is no longer possible to find new investments. Despite being illegal in many countries, Ponzi schemes are now proliferating on Bitcoin, and they keep alluring new victims, who are plundered of millions of dollars. We apply data mining techniques to detect Bitcoin addresses related to Ponzi schemes. Our starting point is a dataset of features of real-world Ponzi schemes, that we construct by analysing, on the Bitcoin blockchain, the transactions used to perform the scams. We use this dataset to experiment with various machine learning algorithms, and we assess their effectiveness through standard validation protocols and performance metrics. The best of the classifiers we have experimented can identify most of the Ponzi schemes in the dataset, with a low number of false positives.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Dissecting Ponzi schemes on Ethereum: identification, analysis, and impact

Ponzi schemes are financial frauds where, under the promise of high profits, users put their money, recovering their investment and interests only if enough users after them continue to invest money. Originated in the offline world 150 years ago, Ponzi schemes have since then migrated to the digital world, approaching first on the Web, and more recently hanging over cryptocurrencies like Bitcoi...

متن کامل

Analyzing the Bitcoin Ponzi Scheme Ecosystem

This paper analyzes the supply and demand for Bitcoinbased Ponzi schemes. There are a variety of these types of scams: from long cons such as Bitcoin Savings & Trust to overnight doubling schemes that do not take off. We investigate what makes some Ponzi schemes successful and others less so. By scouring 11 424 threads on bitcointalk. org, we identify 1 780 distinct scams. Of these, half lasted...

متن کامل

The Age of DIY

R ecently, a friend asked me to write about Bitcoin. This has always been an interesting topic. I wrote about electronic cash in 1997, 1 when the November/December issue of this magazine ran a theme on the topic. My advice then, as now, was " Hold on to your wallet. " After looking into Bitcoin, I realized I couldn't add much to what you can get on this interesting topic yourself, starting with...

متن کامل

There's No Free Lunch, Even Using Bitcoin: Tracking the Popularity and Profits of Virtual Currency Scams

We present the first empirical analysis of Bitcoin-based scams: operations established with fraudulent intent. By amalgamating reports gathered by voluntary vigilantes and tracked in online forums, we identify 192 scams and categorize them into four groups: Ponzi schemes, mining scams, scam wallets and fraudulent exchanges. In 21% of the cases, we also found the associated Bitcoin addresses, wh...

متن کامل

Rejecting the arguments of the sanctity of bitcoin mining and proving its legitimacy by Reward Contract (Joaleh)

Bitcoin soon attracted the attention of experts and the general public around the world, including the Islamic community. Due to the novelty of the subject, although little research has been done to examine the legitimacy of bitcoin mining from the perspective of Muslim thinkers, this paper is responsible for examining two reasons in the research of contemporary Sunni thinkers. The two reasons ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2018