Abstract The integration of quantum computing and agentic artificial intelligence presents a transformative paradigm for advancing cybersecurity frameworks. Quantum algorithms enable accelerated computation for complex tasks such as encrypted traffic analysis and zero-day detection, while agentic intelligence—driven by autonomous, goal-oriented reasoning—provides adaptive and resilient responses against evolving threats. In this work, we propose a hybrid agentic quantum-AI cybersecurity framework that unites quantum machine learning with agent-based decision-making to enhance real-time intrusion detection and automated defense. The framework was evaluated on three benchmark and modern datasets: NSL-KDD, CIC-IDS2017, and CSE-CIC-IDS2018. Results demonstrate that the proposed system achieves up to 42% improvement in detection accuracy and 55% reduction in threat response latency compared to conventional baselines including CNN, Random Forest, Transformer, and A3C models. Quantum modules were implemented and simulated using Qiskit and PennyLane, with scalability considerations discussed for near-term quantum devices. Beyond accuracy, the framework also addresses interpretability, policy-driven response thresholds. This work contributes a novel, rigorous foundation for quantum-accelerated, agentic cybersecurity, balancing proactive defense with adaptive mitigation for emerging threats.
Shaw et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: