LMAE4Eth combines a transaction-to-text language model, a masked graph autoencoder, and cross-attention fusion to detect Ethereum phishing accounts, reporting 6-10% F1 gains over baselines.
Blockchain challenges and opportunities: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding
LMAE4Eth combines a transaction-to-text language model, a masked graph autoencoder, and cross-attention fusion to detect Ethereum phishing accounts, reporting 6-10% F1 gains over baselines.