International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/3113 2020 2020 Department of Computer Science, College of Computer, Qassim University, Buraydah, Saudi Arabia Abdalla Abdalla Department of Computer Science, College of Computer, Qassim University, Buraydah, Saudi Arabia Mohammed Abdullah Al Al-Hagery Cyber-attacks involve a large number of malicious events including phishing, malware attacks, ransomware, social engineering, etc. Automatic cyber-attack recognition and classification are obtained by different technologies and techniques, including artificial intelligence (AI), data analytics, machine learning (ML), deep learning (DL), and other forward-thinking approaches. As a generality of the fuzzy set (FS) and intuitionistic FS (IFS), the Neutrosophic set (NS) can handle incongruous, uncertain, and indeterminacy data where the indeterminate is explicitly measured, and the degree of truth, indeterminacy, and false functions are liberated. It may successfully define inconsistent, uncertain, and incomplete data and overcome certain limitations of the present techniques in representing uncertain decision data. The indeterministic portion of uncertain information, presented in the NS concept, has been instrumented in proper decision-making that is impossible by the IFS concept. Cyber threat detection and classification is a crucial research area that develops intelligent systems that can identify and categorize a variety of cyber-attacks in real time. This article develops an Integrating Machine Learning with Two-Person Intuitionistic Neutrosophic Soft Games for Cyber threat Detection in Blockchain Environment (IMLTPIN-CDBE) system. The main aim of the IMLTPIN-CDBE methodology lies in the automatic recognition of the cyber-threat BC platform.  The initial phase of data normalization using a min-max scalar is conducted in the IMLTPIN-CDBE method. Moreover, the two-person intuitionistic neutrosophic soft games (TPINSSG) technique is applied for cyberattack recognition. Finally, the grasshopper optimization algorithm (GOA) technique is applied for fine-tuning the hyperparameter included in the TPINSSG classifiers. A sequence of experiments has been conducted on the ransomware database to exhibit the great performance of the IMLTPIN-CDBE method. The empirical findings show the supremacy of the IMLTPIN-CDBE method over other current approaches. 2025 2025 33 43 10.54216/IJNS.250204 https://www.americaspg.com/articleinfo/21/show/3113