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
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
