S M Mostaq Hossain, Amani Altarawneh, Jesse Roberts
As blockchain technology and smart contracts become widely adopted, securing them throughout every stage of the transaction process is essential. The concern of improved security for smart contracts is to find and detect vulnerabilities using classical Machine Learning (ML) models and fine-tuned Large Language Models (LLM). The robustness of such work rests on a labeled smart contract dataset that includes annotated vulnerabilities on which several LLMs alongside various traditional machine learning algorithms such as DistilBERT model is trained and tested. We train and test machine learning algorithms to classify smart contract codes according to vulnerability types in order to compare model performance. Having fine-tuned the LLMs specifically for smart contract code classification should help in getting better results when detecting several types of well-known vulnerabilities, such as Reentrancy, Integer Overflow, Timestamp Dependency and Dangerous Delegatecall. From our initial experimental results, it can be seen that our fine-tuned LLM surpasses the accuracy of any other model by achieving an accuracy of over 90%, and this advances the existing vulnerability detection benchmarks. Such performance provides a great deal of evidence for LLMs' ability to describe the subtle patterns in the code that traditional ML models could miss. Thus, we compared each of the ML and LLM models to give a good overview of each model's strengths, from which we can choose the most effective one for real-world applications in smart contract security. Our research combines machine learning and large language models to provide a rich and interpretable framework for detecting different smart contract vulnerabilities, which lays a foundation for a more secure blockchain ecosystem.
Introduction The 18 th Amendment to the 1973 Constitution of Pakistan disentangles overlapping spending responsibilities between the federation and provinces in a wide range of functions, devolving them to the latter. The legislation was also a reaction to relatively poor service delivery and living standards that had fallen continuously behind those in other countries in South Asia, and, indeed, are now lower than sub-Saharan Africa in most respects. The Musharraf government had used this argument for its own decentralization effort—delegating power to the districts and bypassing the political centers of power in the provinces. The 18 th Amendment reasserts the provinces' power and the associated political centers of power. It is designed to weaken the center, and correspondingly make it less attractive for the military to assume power by moving against an elected Prime Minister, as it has done periodically in Pakistan's history. But will this major reform work effectively and ensure higher living standards for all people in all the provinces? To what extent is the need for a national identity important in ensuring that the decentralization does not cause the federation to unravel or the overall delivery of public services to deteriorate and lead to greater exclusion of the poor? These are important issues and could well determine the fate of the 18 th Amendment as well as social stability in Pakistan. Section 2 outlines developments in theory linking governance and the decentralization process. The links between the two are critical. The main question is whether decentralized service provision can better provide for the poorer sections of society by utilizing information that may be available at the local level in tailoring services to local preferences and making access easier. How are these responsibilities financed? Does the process impede closer economic integration between the federating provinces? This chapter argues that positive approaches to intergovernmental reforms, as exemplified by the People's Republic of China, are perhaps more important for countries such as Pakistan that face significant structural challenges.
Politics and Conflicts in Afghanistan, Pakistan, and Middle East