Cognitive Cyber Crimes in the Era of Artificial Intelligence

28Block Chain for Detecting Financial Accounting Risk

Kriti Bhaswar Singh¹*, Abhishek Singh², S.K. Singh³ and Sanjeev Gupta⁴

¹Department of Commerce and Financial Studies, Central, University of Jharkhand, Jharkhand, India

²RATM, Mathura, India

³School of Commerce & Business Studies, Jiwaji University, Gwalior (MP), India

⁴Department of Commerce, Vrinda Sahay Govt. PG College (MP), Madhya Pradesh, India

Abstract

This study proposes a blockchain-enabled framework for detecting financial accounting risk by integrating immutable ledger technology with machine learning analytics. The Financial Statement Fraud dataset from the Center for Research in Security Prices and Compustat (1990–2023) was used, comprising 12,450 firmyear observations with labeled fraudulent and nonfraudulent cases. The proposed method, termed Blockchain-Integrated Risk Detection Network, combines a blockchain-based audit trail for data integrity with a hybrid attention-driven deep neural network for anomaly detection. Experimental evaluation demonstrated a detection accuracy of 97.6%, precision of 96.8%, recall of 97.1%, and F1 score of 96.9%, while achieving an area under precision–recall curve of 0.982. Notably, the blockchain layer reduced data tampering risk by 99.3% and improved Audit Transparency Index by 85.4% compared to conventional systems. These results highlight the effectiveness of blockchain-anchored detection models in enhancing financial accountability and minimizing accounting risk.

Keywords ...