An Efficient SuperHyperSoft Framework for Evaluating LLMs-based Secure Blockchain Platforms

Abstract

 In the age of modern technology, the use of the internet has become imperative. 
However, this widespread access presents a double-edged sword and opens doors for hackers and 
scammers to exploit vulnerabilities and engage in illegal activities. Accordingly, scholars and 
stakeholders are attempting to solve this matter. Large Language Models (LLMs) have provided 
highly effective methodologies and solutions in various cybersecurity sectors. Hence, we exhibited 
the efficacy of LLMs in several information and communication technologies (ICT) such as the 
Internet of Things (IoT), cloud computing, blockchain technology (BCT)…etc which are attacked 
and threatened. Accordingly, the objective of our study is to illustrate how LLMs are supporting 
ICT, especially BC to be secure against attacks. Another study’s objective is to aid the stakeholders 
and enterprises that seek resilience and sustainability by recommending the most secure BC 
platform to adopt in critical sectors. Wherein, LLMs support BC in many directions as developing 
secure smart contracts and scanning the smart contract to protect it from any subversive acts by 
identifying anomalous activities. Hence, we suggested a soft opting model to rank the alternatives 
of BC platforms and recommend optimal BC. Also, the process of constructing this model requires 
leveraging several techniques. We applied for the first time SuperHyperSoft (SHS) as an extension 
of Hypersoft to treat various attributes and sub-attributes for BC based on LLMs. Multi-criteria 
decision-making (MCDM)techniques are utilized for their ability to treat conflicting sub-attributes. 
Hence, entropy and multi-objective optimization based on simple ratio analysis (MOOSRA) are 
utilized as techniques of MCDM. These techniques are working under the authority of the Single 
Value Neutrosophic (SVN) technique to support MCDM techniques in ambiguous situations.  

DOI: 10.5281/zenodo.13380179