Cryptocurrency fraude
Bennett Kleinberg
Department of Security and Crime Science & Dawes Centre for Future Crime, University College London
De drie fases van een pump-and-dump operatie (Kamps & Kleinberg, 2018)
What could go wrong?
The recent explosion of nearly 2,000 cryptocurrencies in a largely unregulated environment has greatly expanded the scope for abuse.
When the tweet was first broadcast at around 3 p.m. ET, GVT was bought and sold on the market at $30.
When the tweet was first broadcast at around 3 p.m. ET, GVT was bought and sold on the market at $30.
By 3:04, it was at $45, and trading volume had doubled.
When the tweet was first broadcast at around 3 p.m. ET, GVT was bought and sold on the market at $30.
By 3:04, it was at $45, and trading volume had doubled.
But by 3:19, GVT’s price had fallen back to $30.29.
But by 3:19, GVT’s price had fallen back to $30.29.
The smart money — the early money — had gotten out, leaving the late money holding a bag of now-diminished value.
Oude uitdagingen | Nieuwe uitdagingen |
---|---|
lage market cap | kortere tijd (bijna real-time) |
gebrek aan informatie | grotere verspreiding van misinformatie |
zeer lage prijs | nieuwe vormen van geruchten |
Data + code https://osf.io/827wd/
Conditional local point anomaly detection
Balanced parameters | |
---|---|
Estimation window | 12h |
Volume increase | 300% |
Price increase | 5% |
Price drop | 1.00 SD |
Alleged pumps | 2150 |
Pump-and-dumps | 1617 |
Crypto/crypto | 97.0% |
Low market cap | 81.8% |
“High-potential coins and coin malleability”
Arguably, the decision to choose one coin for a pump-and-dump scheme and not another are not random but rather subject to cost-benefit processes.
[…] if one is targeting a coin for a P&D, it is useful to be able to manipulate a coin’s price as much as possible, while using the least amount of capital
“the percentage price increase that a coin would experience, with respect to a certain amount of volume injected”
Not all coins are equal!
Klassieke stappen:
Maar hoezo maakt het uit?
Klopt!
Maar: het maken van mainstream gaat sneller dan gedacht
Realistisch: ground truth data + detectie
Realistisch: ground truth data + detectie
Ja Misschien Nee
Promovendi + post-docs: Josh Kamps, Florian Hetzel, Eray Akartuna