Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
This paper provides a systematic analysis of the opportunities, challenges, and potential solutions of harnessing Large Language Models (LLMs) such as GPT-4 to dig out vulnerabilities within smart contracts based on our ongoing research. For the task of smart contract vulnerability detection, achieving practical usability hinges on identifying as many true vulnerabilities as possible while minimizing the number of false positives. Nonetheless, our empirical study reveals contradictory yet interesting findings: generating more answers with higher randomness largely boosts the likelihood of producing a correct answer but inevitably leads to a higher number of false positives. To mitigate this tension, we propose an adversarial framework dubbed GPTLENSthat breaks the conventional one-stage detection into two synergistic stages - generation and discrimination, for progressive detection and refinement, wherein the LLM plays dual roles, i.e., AUDITOR and CRITIC, respectively. The goal of AUDITOR is to yield a broad spectrum of vulnerabilities with the hope of encompassing the correct answer, whereas the goal of CRITIC that evaluates the validity of identified vulnerabilities is to minimize the number of false positives. Experimental results and illustrative examples demonstrate that AUDITOR and CRITIC work together harmoniously to yield pronounced improvements over the conventional one-stage detection. GPTLENSis intuitive, strategic, and entirely LLM-driven without relying on specialist expertise in smart contracts, showcasing its methodical generality and potential to detect a broad spectrum of vulnerabilities. Our code is available at: https://github.com/git-disl/GPTLens.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · cited 1×
“Integrating Generative AI agents: Generative AI agents [27], [50] employ LLMs as the core component and perform specific roles in various tasks like software development [30].”
MethodGenerative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093 · cited 1×
“Recently, generative large language models [5], [26], [57] (LLMs) are rapidly emerging and reshaping the domain of software engineering [15], facilitating tasks of code generation [9], code understanding [45], and code repair [28].”
BackgroundA Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2305.10601 · Cited by 1,158
Toolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
Cited by
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083
“As shown in Table 2, a comparison with state-of-the-art methods reveals that the majority of researchers (17 out of 25) have concluded that LLM-based methods outperform traditional approaches (advantages include higher code coverage, higher detecting accuracy, less cost etc.).”
BackgroundInfluentialWhen LLMs meet cybersecurity: a systematic literature review
Zhang, J., Bu, H., Wen, H., Liu, Y., Fei, H., Xi, R., Li, L., Yang, Y., Zhu, H., & Meng, D. (2025) · Cybersecurity · doi:10.1186/s42400-025-00361-w · Cited by 383
“It compares the original code with LLM-generated code to flag notable differences as anomalies for further inspection.”
A Survey on Large Language Model-Based Game Agents
Hu, S., Huang, T., Liu, G., Kompella, R. R., Ilhan, F., Tekin, S. F., Xu, Y., Yahn, Z., & Liu, L. (2024) · arXiv · doi:10.48550/arxiv.2404.02039 · Cited by 165
Self-citationJaffal, N. O., Alkhanafseh, M., & Mohaisen, D. (2025) · AI · doi:10.3390/ai6090216 · Cited by 69
Large Language Model-Based Agents for Software Engineering: A Survey
Liu, J., Wang, K., Chen, Y., Peng, X., Chen, Z., Zhang, L., & Lou, Y. (2024) · arXiv · doi:10.48550/arxiv.2409.02977 · Cited by 49
Metadata
- Authors
- Hu, S., Huang, T., İlhan, F., Tekin, S. F., & Liu, L.
- Venue
- 2023 5th IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)
- Publisher
- IEEE
- Published
- 2023-11-01
- Pages
- 297-306
- OpenAlex
- W4391877140
- Cited by
- 85
- References
- 20
- FWCI
- 22.65
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives. https://app.cochat.ai/papers/10.1109/tps-isa58951.2023.00044
- The paper
- Hu, S., Huang, T., İlhan, F., Tekin, S. F., & Liu, L. (2023). Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives. 2023 5th IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA). https://doi.org/10.1109/tps-isa58951.2023.00044
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.