Esteban Miño
@estebanmino.eth
I did it. I can flag scam tokens on Base. (With 94% accuracy)
1 reply
0 recast
2 reactions
Esteban Miño
@estebanmino.eth
Instead of attempting smart contract audits, I developed a neighborhood-based algorithm, based by the principle: If you interact with a scammer, you're also likely a scammer. I trained graph neural network models to understand: • How tokens interact • The behavior of their neighborhoods • Subgraph patterns that indicate scams
3 replies
0 recast
1 reaction
Esteban Miño
@estebanmino.eth
Here’s one example of the scam behavior my model can flag: 1. A “Token Deployer” wallet gets funded by a “Malicious Wallet” to deploy the “Target Token.” 2. Adds 100 ETH liquidity to a decentralized exchange. 3. Removes liquidity for 118 ETH, sending it back to the funding wallet. The algorithm also detects subgraphs of related tokens interacting via middle-man wallets, flagging broader networks of malicious behavior. You can see 4 other tokens in red. 🚩 And finally, turns out the "Malicious Wallet" has thousands of transactions following this model.
0 reply
0 recast
0 reaction
Esteban Miño
@estebanmino.eth
Testing different GNN algorithms, the best results: • Accuracy (94.94%): This represents the overall percentage of tokens correctly classified as scams or safe. • Precision (91.59%): Of all tokens flagged as scams, 91.59% were indeed scams, indicating a low rate of false alarms (WIP). • Recall (100.00%): Every scam token was successfully identified, with none slipping through. • False Positives (11.25%): 11.25% of safe tokens were incorrectly flagged as scams (WIP). • False Negatives (0.00%): No scam tokens were missed, achieving an absolute zero in missed threats.
0 reply
0 recast
0 reaction
Esteban Miño
@estebanmino.eth
Why am I doing this? While in SF some days ago, I was blown away by what’s happening in the AI space. So I'm giving it a try. I believe AI algorithms can far beat us reading data from a blockchain. I'm experimenting with this idea to expand its applications beyond just scam alerts. If you have ideas please let me know. But first, I need to make it work in real time.
0 reply
0 recast
0 reaction
thesolenoid.base.eth
@solomonadzape
Woah Nice one man
0 reply
0 recast
0 reaction
