The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
LLM Assisted Dual-View Awareness Framework for Smart Contract Vulnerability Detection
Abstract
Smart contract vulnerability detection is an important task in securing the blockchain. However, existing detection methods primarily extract single view features, such as semantic or structural features, which ignores the synergistic supplementation of them to smart contract, remaining room for improvement in feature representation. To this end, this paper proposes the LLM-assisted dual-view awareness framework for smart contract vulnerability detection, which incorporates significantly different semantic features and structural features. To address the limitation of large language model (LLM) in domain-specific expertise, we design semantic awareness module based on Retrieval-Augmented Generation (RAG), construct vulnerability knowledge base, and perform semantic reasoning on smart contracts. To capture crucial structural information, we propose structural awareness module based on Graph Neural Network (GNN), construct contract graphs, and perform structural analysis on smart contracts. We evaluated four types of vulnerabilities, and the experimental results show that our approach significantly outperforms state-of-the-art approaches, achieving 4.80% improvement in accuracy for timestamp dependence detection.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Multi-agent smart-contract auditors [119,121-123,125] now match or exceed expert auditors on standard benchmarks.”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [119]
Citations
Cites
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688 · cited 1×
“However, due to their intrinsic characteristics as lexical probabilistic models, LLMs lack the capacity for formal syntactic analysis and exhibit high false positive rate, which require further validation in later stages [24, 25].”
Rethinking Smart Contract Fuzzing: Fuzzing With Invocation Ordering and Important Branch Revisiting
Liu, Z., Qian, P., Yang, J., Liu, L., Xu, X., He, Q., & Zhang, X. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3237370 · Cited by 138
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Fakhoury, S., Naik, A., Sakkas, G., Chakraborty, S., & Lahiri, S. K. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3428972 · Cited by 120
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Fakhoury, S., Naik, A., Sakkas, G., Chakraborty, S., & Lahiri, S. K. (2024) · arXiv · doi:10.48550/arxiv.2404.10100
Research works printed but not linked: 51
- 10.1016/j.scs.2024.105717 · DOI
- 10.1016/j.ijepes.2021.107515 · DOI
- 10.1016/j.rser.2021.112013 · DOI
- 10.1145/3593293 · DOI
- 10.1145/3548606.3559384 · DOI
- G. W, 2023, Vulnerability in curve finance vyper code leads to multi-million dollar hack affecting several liquidity pools, Chainalysis
- 2024, Sumermoney hack analysis, Medium
- 10.1109/TSE.2021.3116808 · DOI
- 10.1145/3533767.3534395 · DOI
- Sunbeom So, Smartest: Effectively hunting vulnerable transaction sequences in smart contracts through language model-guided symbolic execution, 1361
- 10.1145/3658644.3691365 · DOI
- 10.1109/ISSRE.2019.00052 · DOI
- Nguyen, Sfuzz: An efficient adaptive fuzzer for solidity smart contracts, 778
- 10.1109/INFOCOM52122.2024.10621414 · DOI
- 10.1016/j.jksuci.2022.08.029 · DOI
- 10.1145/3464421 · DOI
- Luo, Scvhunter: Smart contract vulnerability detection based on heterogeneous graph attention network, 1
- 10.1109/TKDE.2021.3095196 · DOI
- 10.1145/3597503.3639117 · DOI
- 10.1007/s10664-024-10602-0 · DOI
- 10.1145/3663529.3664458 · DOI
- 10.1145/3702973 · DOI
- 10.1145/3391195 · DOI
- 10.1145/3543507.3583367 · DOI
- 10.1007/s10664-024-10446-8 · DOI
- 10.1016/j.comnet.2022.109289 · DOI
- Registry, Smart contract weakness classification
- Korsholm, 2024, Mastering prompt engineering: A comparative guide to nine prompt engineering frameworks for tech professionals, Linkedin
- 10.24963/ijcai.2020/454 · DOI
- 10.24963/ijcai.2021/379 · DOI
- Tikhomirov, Smartcheck: Static analysis of ethereum smart contracts, 9
- 10.1145/2976749.2978309 · DOI
- Mythril: security analysis tool for evm bytecode, GitHub
- 10.1109/WETSEB.2019.00008 · DOI
- 10.1016/j.scico.2024.103172 · DOI
- 10.1109/ISSRE52982.2021.00047 · DOI
- 10.1109/TPS-ISA58951.2023.00044 · DOI
- Wei, 2024, Llm-smartaudit: Advanced smart contract vulnerability detection, arXiv preprint arXiv:2410.09381 · arXiv
- Wei, 2025, Ftsmartaudit: A knowledge distillation-enhanced framework for automated smart contract auditing using fine-tuned llms, arXiv preprint arXiv:2410.13918 · arXiv
- Qian, Smart-contract-dataset, GitHub
- 10.1016/S0306-4573(02)00021-3 · DOI · Paper page
- 10.1561/1500000019 · DOI · Paper page
- 10.1016/j.comnet.2022.109289 · DOI
- 10.1038/s41598-023-47219-0 · DOI
- 10.1109/ISSRE59848.2023.00025 · DOI
- 10.1016/j.jss.2022.111550 · DOI
- Wu, Advscanner: Generating adversarial smart contracts to exploit reentrancy vulnerabilities using llm and static analysis, 1019
- 10.1109/icse55347.2025.00027 · DOI
- 10.1109/ISSRE59848.2023.00030 · DOI
- 10.1145/3551349.3560428 · DOI
- 10.1109/ISSRE59848.2023.00024 · DOI
Cited by
Sorted by citations
Nageshwaran, V., & Ezekiel, S. (2026) · Electronics · doi:10.3390/electronics15122740 · Cited by 4
“Multi-agent smart-contract auditors [119,121–123 , Compared to coverage-guided fuzzers such as AFL++ and libFuzzer—which excel at exploring branch space within a single binary but treat every input byte as opaque—LLM-driven discovery contributes three capabilities.”
Metadata
- Authors
- Wang, J., Yue, Y., Hu, D., Li, Q., Li, J., & Zhu, W.
- Affiliations
- Tianjin University (CN)
- Tianjin Renai College (CN)
- Venue
- 2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE)
- Publisher
- IEEE
- Published
- 2025-10-21
- Pages
- 95-106
- ISSN
- 1071-9458 (ISSN-L)
- OpenAlex
- W4416222603
- Cited by
- 1
- References
- 4
- Citations by year
- 2026: 1
- FWCI
- 1.20
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings/Proceedings - International Symposium on Software Reliability Engineering (publishedVersion)
- Funders
- Tianjin University
- Topics
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- smart contract vulnerability detection, large language models, semantic features, structural features, retrieval-augmented generation, graph neural networks, blockchain security
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
