Counterfeiting and cybersecurity threats are two major challenges the global supply chain faces and requires extensive solutions for authenticity, security, and transparency. In some earlier work, we used machine learning in ML techniques to improve supply chain security by detecting anomalies and fraudulent activities. The emergence of quantum computing has introduced new weaknesses in existing cryptography techniques, thus requiring the development of anti-quantum solutions. This paper introduces a novel framework that integrates post-quantum cryptography (PQC) and machine learning (ML)-driven anomaly detection to secure blockchain-based supply chains against new threats. PQC protects blockchain data via quantum-secure encryption of transactions, while ML models analyze real-time delivery data for anomaly detection and fraud prevention. In addition, the system incorporates IoT tools for real-time monitoring, advanced tokenization for traceability, smart contract enforcement automation, and a hybrid consent mechanism to ensure user-friendliness. Through medical data analysis, the system demonstrates an ability to reduce counterfeiting and to improve stakeholder confidence and to establish flexible, future-proof supply chains.
Keywords: Block chain technology, Block chain-Enabled Unique Identification System (BEUIS), counterfeit drugs, public health, web application, supply chain
How to cite this article: Kalpana R, Sridevi S, A Post-Quantum Cryptography and Machine Learning-Driven Framework for Securing Blockchain-Based Supply Chain. Int J Drug Deliv Technol. 2026;16(4s): 30-43; DOI: 10.25258/ijddt.16.30-43