Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62608
Volume:
10 |
5 |
May 2026
Pages:
1-11
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
Amity Institute of Information Technology
Amity University Raipur Chhattisgarh
The intersection of quantum computing and artificial intelligence (AI) poses both an immediate risk and a distinct chance for digital security. As adversaries with quantum capabilities come closer to being able to compromise commonly used public-key systems, the need for adopting quantum-resistant cryptographic primitives becomes essential. At the same time, AI and machine learning (ML) technologies are continuously transforming how security systems identify threats, respond to changing risks, and automate crucial lifecycle decisions. This study presents an innovative framework—an AI-Enhanced Post-Quantum Security System (AI-EPQSS)—that integrates AI entities throughout telemetry gathering, threat prediction, dynamic policy mechanisms, and automated Key management by utilizing a combination of post-quantum and quantum resistant methodologies for key administration in the active environment. Ideally suited for both classical and post-quantum hybrid implementations, the model provides a means of dynamically selecting algorithms, supports federated learning between nodes and includes adversarially resistant AI reasoning as a means of additional security or protection. A proof of concept evaluation demonstrates that the developed model provides less latency, more throughput, greater quantum attack protection, and significantly less risk exposure when compared to previously established non-adaptive models or to those that were solely reliant upon PQC. This research supports the management of cryptographic agility during this period of quantum evolution, and directs future developments towards developing operationally feasible AI-augmented cryptographic systems.
KEYWORDS
The results demonstrate the increased performance and security of the AI-PQSS over the other two models. The AI-PQSS showed the fastest times for key generation, encryption, and decryption compared to both old security models due to its ability to adapt to new environments with the use of artificial intelligence and hybrid cryptography. Additionally, the AI-PQSS demonstrates exceptional throughput and thus demonstrates improved data management capabilities within secure environments. The AI-PQSS demonstrated a Quantum Attack Resistance Index of .97: showing strength against representative future evolving quantum threats. Also, the AI-PQSS demonstrated the lowest Security Risk Index of .09: this shows that the AI-PQSS model is capable of detecting and preventing anomalies effectively. Based on these visual results, the AI-PQSS has enhanced speed and security due to its use of AI-enhanced cryptography. Furthermore, the AI-PQSS can quickly adjust to the constantly changing conditions of the digital space and the potential adversities it faces. Therefore, it is capable of maintaining a high level of performance during periods when computing is under extreme pressure. The continuous improvement of its encryption strategies is done using Reinforcement Learning, which is further bolstered by Federated Intelligence for improved decentralization of security, thus this very flexibility is a great asset in its advancement of post-quantum cryptography.
[1] M. Alvarado, L. Gayler, A. Seals, T. Wang and T. Hou, “A Survey on Post-Quantum Cryptography: State-of-the-Art and Challenges,” arXiv preprint arXiv:2312.10430, Dec. 2023. [2] “A Survey of Post-Quantum Cryptography: Start of a New Race,” MDPI, 2023. [3] P. Radanliev et al., “Artificial Intelligence and Quantum Cryptography,” Journal of Analytical Science and Technology, 2024. [4] M. E. Paul, F. Osholake, and J. Ederhion, “Using Machine Learning to Enhance Post-Quantum Cryptographic Algorithms,” IJAEM, May 2024. [5] N. Ahmed, L. Zhang, and A. Gangopadhyay, “A Survey of Post-Quantum Cryptography Support in Cryptographic Libraries,” arXiv, Aug. 2025. [6] “Post-Quantum Cryptography,” NIST Computer Security Resource Center, 2024. [7] “Post-Quantum Cryptography Awareness Is High, But Widespread Action Lags,” Entrust Cybersecurity Institute Report, Oct. 2024. [8] “Post-Quantum Cryptography for AI-Driven Cloud Security Solutions,” IJFMR, 2024. [9] G. Chhetri, S. Somvanshi, P. Hebli, S. Brotee, and S. Das, “Post-Quantum Cryptography and Quantum-Safe Security: A Comprehensive Survey,” arXiv, Oct. 2025. [10] “Post Quantum Cryptography: A Survey of Past and Future,” ResearchGate, 2024.
Publication Date
5/6/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...