Yao Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yao Tan has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Fan Yang
China University of Geosciences
2 shared publications - Jun Song
China University of Geosciences
2 shared publications - Xue Liang
School of Computer Science, China University of Geosciences, Wuhan 430074, China
2 shared publications
Latest Publications
- Open Access
- 9 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (19) , 10844
Contract-Graph Fusion and Cross-Graph Matching for Smart-Contract Vulnerability Detection
Smart contracts empower many blockchain applications but are exposed to code-level defects. Existing methods do not scale to the evolving code, do not represent complex control and data flows, and lack granular and calibrated evidence. To address the above concerns, we present an across-graph corresponding contract-graph method for vulnerability detection: abstract syntax, control flow, and data flow are fused into a typed, directed contract-graph whose nodes are enriched with pre-code embeddings (GraphCodeBERT or CodeT5+). A Graph Matching Network (GMN) with cross-graph attention compares contract-graphs, aligns homologous sub-graphs associated with vulnerabilities, and supports the interpretation of statements at the level of balance between a broad structural coverage and a discriminative pairwise alignment. The evaluation follows a deployment-oriented protocol with thresholds fixed for validation, multi-seed averaging, and a conservative estimate of sensitivity under low-false-positive budgets. On SmartBugs Wild, the method consistently and markedly exceeds strong rule-based and learning baselines and maintains a higher sensitivity to matching false-positive rates; ablations track the gains to multi-graph fusion, pre-trained encoders, and cross-graph matching, stable through seeds.
- 9 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (19) , 10844
Open AccessContract-Graph Fusion and Cross-Graph Matching for Smart-Contract Vulnerability Detection
Smart contracts empower many blockchain applications but are exposed to code-level defects. Existing methods do not scale to the evolving code, do not represent complex control and data flows, and lack granular and calibrated evidence. To address the above concerns, we present an across-graph corresponding contract-graph method for vulnerability detection: abstract syntax, control flow, and data flow are fused into a typed, directed contract-graph whose nodes are enriched with pre-code embeddings (GraphCodeBERT or CodeT5+). A Graph Matching Network (GMN) with cross-graph attention compares contract-graphs, aligns homologous sub-graphs associated with vulnerabilities, and supports the interpretation of statements at the level of balance between a broad structural coverage and a discriminative pairwise alignment. The evaluation follows a deployment-oriented protocol with thresholds fixed for validation, multi-seed averaging, and a conservative estimate of sensitivity under low-false-positive budgets. On SmartBugs Wild, the method consistently and markedly exceeds strong rule-based and learning baselines and maintains a higher sensitivity to matching false-positive rates; ablations track the gains to multi-graph fusion, pre-trained encoders, and cross-graph matching, stable through seeds.
- Open Access
- 11 September 2025
- Published by MDPI AG in Preprints.org
Contract-Graph Fusion and Cross-Graph Matching for Smart-Contract Vulnerability Detection
Smart contracts empower many blockchain applications but are exposed to code-level defects. Existing methods do not scale to the evolving code, do not represent complex control and data flows, and lack granular and calibrated evidence. To address the above concerns, we present a across-graph correspondering contract-graph method for vulnera bility detection: abstract syntax, control flow, and data flow are fused into a typed, directed contract graph whose nodes are enriched with pre-code embeddings (GraphCodeBERT or CodeT5+). A Graph Matching Network with cross-graph attention compares contract graphs, aligns homologous subgraphs associated with vulnerabilities, and supports the interpretation of statements at the level of balance between a broad structural coverage and a discriminative pairwise alignment. The evaluation follows a deployment-oriented protocol with thresholds fixed for validation, multi-seed averaging and a conservative estimate of sensitivity under low false-positive budgets. On SmartBugs Wild, the method consistently and markedly exceeds strong rule-based and learning baselines and maintains a higher sensitivity to matching false positive rates; ablations track the gains to multi-graph fusion, pre-trained encoders and cross-graph matching, stable through seeds.
- 11 September 2025
- Published by MDPI AG in Preprints.org
Open AccessContract-Graph Fusion and Cross-Graph Matching for Smart-Contract Vulnerability Detection
Smart contracts empower many blockchain applications but are exposed to code-level defects. Existing methods do not scale to the evolving code, do not represent complex control and data flows, and lack granular and calibrated evidence. To address the above concerns, we present a across-graph correspondering contract-graph method for vulnera bility detection: abstract syntax, control flow, and data flow are fused into a typed, directed contract graph whose nodes are enriched with pre-code embeddings (GraphCodeBERT or CodeT5+). A Graph Matching Network with cross-graph attention compares contract graphs, aligns homologous subgraphs associated with vulnerabilities, and supports the interpretation of statements at the level of balance between a broad structural coverage and a discriminative pairwise alignment. The evaluation follows a deployment-oriented protocol with thresholds fixed for validation, multi-seed averaging and a conservative estimate of sensitivity under low false-positive budgets. On SmartBugs Wild, the method consistently and markedly exceeds strong rule-based and learning baselines and maintains a higher sensitivity to matching false positive rates; ablations track the gains to multi-graph fusion, pre-trained encoders and cross-graph matching, stable through seeds.