Deep Learning-Based Program-Wide Binary Code Similarity for Smart Contracts
Bibliographic record
Abstract
Recently, security issues of smart contracts are arising great attention due to the enormous financial loss caused by vulnerability attacks. There is an increasing need to detect similar codes for hunting vulnerability with the increase of critical security issues in smart contracts. Binary similarity detection that quantitatively measures the given code diffing has been widely adopted to facilitate critical security analysis. However, due to the difference between common programs and smart contract, such as diversity of bytecode generation and highly code homogeneity, directly adopting existing graph matching and machine learning based techniques to smart contracts suffers from low accuracy, poor scalability and the limitation of binary similarity on function level. Therefore, this paper investigates graph neural network to detect smart contract binary code similarity at the program level, where we conduct instruction-level normalization to reduce the noise code for smart contract pre-processing and construct contract control flow graphs to represent smart contracts. In particular, two improved Graph Convolutional Network (GCN) and Message Passing Neural Network (MPNN) models are explored to encode the contract graphs into quantitatively vectors, which can capture the semantic information and the program-wide control flow information with temporal orders. Then we can efficiently accomplish the similarity detection by measuring the distance between two targeted contract embeddings. To evaluate the effectiveness and efficient of our proposed method, extensive experiments are performed on two real-world datasets, i.e., smart contracts from Ethereum and Enterprise Operation System (EOS) blockchain-based platforms. The results show that our proposed approach outperforms three state-of-the-art methods by a large margin, achieving a great improvement up to 6.1% and 17.06% in accuracy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.000 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.006 | 0.005 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".