PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915050608918528 |
|---|---|
| author | Liu, Ye Xue, Yue Wu, Daoyuan Sun, Yuqiang Li, Yi Shi, Miaolei Liu, Yang |
| author_facet | Liu, Ye Xue, Yue Wu, Daoyuan Sun, Yuqiang Li, Yi Shi, Miaolei Liu, Yang |
| contents | With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs,such as GPT-4, to transfer existing human-written properties (e.g.,those from Certora auditing reports) and automatically generate customized properties for unknown code. To this end, we embed existing properties into a vector database and retrieve a reference property for LLM-based in-context learning to generate a new property for a given code. While this basic process is relatively straightforward, ensuring that the generated properties are (i) compilable, (ii) appropriate, and (iii) verifiable presents challenges. To address (i), we use the compilation and static analysis feedback as an external oracle to guide LLMs in iteratively revising the generated properties. For (ii), we consider multiple dimensions of similarity to rank the properties and employ a weighted algorithm to identify the top-K properties as the final result. For (iii), we design a dedicated prover to formally verify the correctness of the generated properties. We have implemented these strategies into a novel LLM-based property generation tool called PropertyGPT. Our experiments show that PropertyGPT can generate comprehensive and high-quality properties, achieving an 80% recall compared to the ground truth. It successfully detected 26 CVEs/attack incidents out of 37 tested and also uncovered 12 zero-day vulnerabilities, leading to $8,256 in bug bounty rewards. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02580 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation Liu, Ye Xue, Yue Wu, Daoyuan Sun, Yuqiang Li, Yi Shi, Miaolei Liu, Yang Software Engineering Artificial Intelligence With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs,such as GPT-4, to transfer existing human-written properties (e.g.,those from Certora auditing reports) and automatically generate customized properties for unknown code. To this end, we embed existing properties into a vector database and retrieve a reference property for LLM-based in-context learning to generate a new property for a given code. While this basic process is relatively straightforward, ensuring that the generated properties are (i) compilable, (ii) appropriate, and (iii) verifiable presents challenges. To address (i), we use the compilation and static analysis feedback as an external oracle to guide LLMs in iteratively revising the generated properties. For (ii), we consider multiple dimensions of similarity to rank the properties and employ a weighted algorithm to identify the top-K properties as the final result. For (iii), we design a dedicated prover to formally verify the correctness of the generated properties. We have implemented these strategies into a novel LLM-based property generation tool called PropertyGPT. Our experiments show that PropertyGPT can generate comprehensive and high-quality properties, achieving an 80% recall compared to the ground truth. It successfully detected 26 CVEs/attack incidents out of 37 tested and also uncovered 12 zero-day vulnerabilities, leading to $8,256 in bug bounty rewards. |
| title | PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2405.02580 |