AI-Driven Approaches to Post-Quantum Cybersecurity: Bridging Quantum Computing Threats and Intelligent Defense Systems
Abstract: Quantum computers will eventually break the encryption schemes protecting most of today's digital infrastructure. Because adversaries can harvest encrypted data now and decrypt it later once that capability exists, organizations face an immediate prioritization problem: which data should be migrated to post-quantum cryptography first? We propose a Quantum Exposure Window (QEW) metric, grounded in published expert forecasts of quantum arrival timelines, combined with a machine-learning anomaly detector that flags likely data-harvesting activity in network telemetry. We tested the resulting scheduling algorithm in a controlled simulation and found that our original design- combining these two signals multiplicatively - failed to prioritize short-lifespan data under active attack. We identify why this happens, derive a corrected additive rule, and prove it eliminates the failure mode; the simulation confirms an improvement from 0% to 75.6% coverage of the affected cases at the same migration budget. We discuss the limits of this validation, including its synthetic nature and an unresolved assumption about linking network anomalies to specific data assets, and outline the real-world testing this would require before deployment.
Keywords: Post-Quantum Cryptography; Artificial Intelligence; Cybersecurity; Threat Detection; Quantum Computing
How to Cite?: Rahul Gandhi, "AI-Driven Approaches to Post-Quantum Cybersecurity: Bridging Quantum Computing Threats and Intelligent Defense Systems", Volume 15 Issue 10, October 2026, International Journal of Science and Research (IJSR), Pages: 206-212, https://www.ijsr.net/getabstract.php?paperid=SR261002112803, DOI: https://dx.doi.org/10.21275/SR261002112803