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.
- TxLucent uses function name sequences instead of source code or handcrafted rules
- 1.56% false negative rate on 424 incidents with 14,611 attack transactions
- Estimated 0.0017% false positive rate across 500M+ Ethereum transactions
- 24.90 ms average analysis time supports real-time detection
From the original article
1 min read at arxiv.orgBlockchain application attacks, targeting business logic bugs in decentralized applications (dApps), have been an increasing concern to their developers and users, causing significant financial loss. Existing attack detectors either rely on handcrafted rules for detection, or need difficult-to-obtain smart contract source code to analyze attack transactions. This makes them brittle and inapplicable in practice.
By Rui Xi · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.