A graph neural network with handcrafted temporal features identifies more Ethereum phishing addresses than one using raw transaction fields, though the phishing-class F1 is 0.28, not the reported 0.95.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Fishing for Phishers: Learning-Based Phishing Detection in Ethereum Transactions
A graph neural network with handcrafted temporal features identifies more Ethereum phishing addresses than one using raw transaction fields, though the phishing-class F1 is 0.28, not the reported 0.95.