60
60
30
30
30
45
60
60
42
30
30
30
55
60
60
30
42
42
30
30
30
30
30
30
57
42
60
60
60
42
42
60
30
55
42
30
60
30
60
Function Name Is All You Need to Detect Blockchain Application Attacks
TxLucent detects blockchain dApp attacks from transaction function-name sequences using a transformer, achieving 1.56% false negatives without source code.
Researchers propose TxLucent, which maps transaction call traces to function name sequences and uses a transformer to detect blockchain application attacks without source code or handcrafted rules. Evaluated on 424 real-world incidents with 14,611 attack transactions, it achieves a 1.56% false negative rate and an estimated 0.0017% false positive rate across over 500 million Ethereum transactions. Average analysis time of 24.90 milliseconds supports real-time detection on popular blockchains.
45