Hanan El Bakkali

Oualid Zaazaa, Hanan El Bakkali

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 LLMdriven rule integration, offering a new approach to improving Blockchain security and addressing previously underexplored vulnerabilities in smart contracts.

Hasnae Rahimi, Hanan EL Bakkali

Robust Trust Reputation Systems (TRS) provide a most trustful reputation score for a specific product or service so as to support relying parties taking the right decision while interacting with an e-commerce application. Thus, TRS must rely on an appropriate architecture and suitable algorithms that are able to improve the selection, storage, generation and classification of textual feedbacks. In this work, we propose a new architecture for TRS in e-commerce applications. In fact, we propose an intelligent layer which displays to each feedback provider, who has already given his recommendation on a product, a collection of prefabricated feedbacks related to the same product. The proposed reputation algorithm generates better trust degree of the user, trust degree of the feedback and a better global reputation score of the product.