A Systematic Review of Deep Learning-Enabled Post-Quantum Blockchain Frameworks for Secure and Sustainable Supply Chain Management

In the interest of global supply chains becoming more data heavy, digital and more vulnerable to adversarial manipulation, blockchain, deep learning, and cryptographic security research have converged. Blockchain ledgers provide an immutable source of origin and trust to multi-party logistics networks, and deep learning models provide predictive and anomaly-detection capabilities to manage demand volatility, sensor noise, and cyber-physical risks at IoT-enabled supply chain points. The cryptographic primitives used in the consensus mechanisms and signature schemes of present-day blockchains and the one currently used in the crypto layer, however, are known to be provably vulnerable to Shor's and Grover's quantum algorithms, placing a long-term security burden on any supply chain infrastructure that relies on classical hardness assumptions. This review aims to present an overview of the twenty-two peer-reviewed and IEEE-indexed papers related to blockchain-based supply chain security, AI-enabled blockchain, federated deep learning, IoT and edge security, post-quantum cryptography (PQC), and quantum-secure blockchain architectures, in order to build a solid understanding of how these four technological layers can be integrated into a coherent supply chain security stack. The review builds a comparative analysis of blockchain frameworks, PQC algorithm families, deep learning architectures, and agriculture, healthcare, vehicular network, geospatial systems and cloud storage, among others. This synthesis is extended to an original taxonomy, which shows the technological evolution from deep learning to blockchain, post-quantum cryptography, supply chain security and sustainability and a conceptual framework composed of 9 layers, going from data collection and IoT sensing, to edge intelligence, federated deep learning, post quantum cryptographic hardening, blockchain consensus, smart contract execution, supply chain analytics and decision support.