SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
Oualid Zaazaa, Hanan El Bakkali

TL;DR
SmartLLMSentry is a novel framework that uses large language models like ChatGPT to improve the detection of vulnerabilities in smart contracts, offering faster and more accurate security assessments for blockchain applications.
Contribution
It introduces a new LLM-based approach for smart contract vulnerability detection, overcoming limitations of traditional rule-based systems and demonstrating effective use of in-context training.
Findings
Achieved 91.1% exact match accuracy with sufficient data.
GPT-4 showed reduced performance compared to GPT-3 in rule generation.
Enhanced speed and accuracy in vulnerability detection.
Abstract
Smart contracts are essential for managing digital assets in blockchain networks, highlighting the need for effective security measures. This paper introduces SmartLLMSentry, a novel framework that leverages large language models (LLMs), specifically ChatGPT with in-context training, to advance smart contract vulnerability detection. Traditional rule-based frameworks have limitations in integrating new detection rules efficiently. In contrast, SmartLLMSentry utilizes LLMs to streamline this process. We created a specialized dataset of five randomly selected vulnerabilities for model training and evaluation. Our results show an exact match accuracy of 91.1% with sufficient data, although GPT-4 demonstrated reduced performance compared to GPT-3 in rule generation. This study illustrates that SmartLLMSentry significantly enhances the speed and accuracy of vulnerability detection through…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsPosition-Wise Feed-Forward Layer · Absolute Position Encodings · Label Smoothing · Linear Layer · Cosine Annealing · Multi-Head Attention · Transformer · Byte Pair Encoding · Weight Decay · {Dispute@FaQ-s}How to file a dispute with Expedia?
