Unveiling Smart Contract Vulnerabilities: A New Approach

Strategic Insights -

Researchers from York University have introduced a novel method for detecting and profiling smart contract vulnerabilities, leveraging an enhanced genetic algorithm and a new benchmark dataset. This approach aims to improve the security of blockchain networks by providing a more accurate and effective solution for identifying vulnerabilities. The research was funded by the Natural Sciences And Engineering Research Council of Canada and the Canada Research Chairs Program.

Key Takeaways:

  • The research proposes a two-component approach, consisting of an updated analyzer named SCsVulLyzer (V2.0) and an advanced Genetic Algorithm (GA) profiling method.
  • The analyzer extracts 240 features across different categories, while the enhanced GA employs techniques such as penalty fitness function, retention of elites, and adaptive mutation rate to create a detailed profile for each vulnerability.
  • A new dataset named BCCC-SCsVul-2024 was introduced, consisting of 111,897 Solidity source code samples, ensuring the practical validation of the proposed approach.
  • The proposed approach demonstrated superior capabilities with higher precision and accuracy through rigorous testing and experimentation.
  • The concept of the profiling technique makes the model highly transparent and explainable.
  • The research highlighted the potential of GA-based profiling to improve the detection and identification of smart contract vulnerabilities.

Statistics:

  • 240 features extracted by the SCsVulLyzer (V2.0) analyzer across different categories.
  • 111,897 Solidity source code samples included in the new dataset BCCC-SCsVul-2024.
  • 3 types of taxonomies established, covering SC literature review, profiling techniques, and feature extraction.
  • The proposed approach demonstrated excellent results for evaluation parameters, including precision and accuracy.

Sources:

  • Unveiling smart contract vulnerabilities: Toward profiling smart contract vulnerabilities using enhanced genetic algorithm and generating benchmark dataset. Blockchain: Research and Applications, 2025, 6(2): 100253. (Source: https://doi.org/10.1016/j.bcra.2024.100253)
  • NewsRx. New Data from York University Illuminate Research in Blockchain Research (Unveiling smart contract vulnerabilities: Toward profiling smart contract vulnerabilities using enhanced genetic algorithm and generating benchmark dataset). Life Science Weekly. June 10, 2025; p 2664.