Quantum-AI cybersecurity threat detection framework: A hybrid architecture for enterprise security operations

Abstract

Enterprise security operations face computational bottlenecks that classical architectures cannot efficiently resolve at scale. This paper presents the quantum-AI cybersecurity threat detection framework (QACTDF), a hybrid architecture that combines quantum-enhanced optimization with AI-driven behavioral analytics for large-enterprise threat detection. The architecture employs a four-layer orchestration model in which an AI-governed routing policy selectively directs security workloads-including threat correlation, cryptographic verification, and anomaly classification-to quantum-assisted processors, while high-throughput tasks such as telemetry ingestion and alert triage are handled by classical infrastructure. Qualitatively evaluated against canonical security framework criteria-detection scope, integration feasibility, scalability, and sustainability-and supported by simulation-derived performance estimates, QACTDF addresses functional capability gaps in conventional security architectures. The framework additionally incorporates post-quantum cryptographic alignment in accordance with NIST FIPS 203 and provides a sequential adoption pathway for enterprise architects integrating quantum capabilities into existing security operations centers.