City Research Online

Abstract

The rapid adoption of Artificial Intelligence (AI) in consumer applications has significantly improved automation and user experiences. However, it has introduced emerging security challenges, particularly AI-driven adversarial attacks. Conventional cryptographic mechanisms are increasingly susceptible to these attacks and to the growing risks associated with quantum computing. To mitigate these challenges, this paper presents an AI-enabled, adversarial attack-resistant, post-quantum secure authentication protocol designed for consumer applications. The proposed protocol combines post-quantum lattice-based cryptographic techniques to provide strong and adaptive user authentication against evolving threats. Comprehensive formal security analysis and experimental evaluations confirm that the protocol effectively mitigates quantum and adversarial attacks, including classical attacks, while maintaining comparable computational and communication overhead with the existing competing authentication schemes. As a result, the proposed scheme becomes ideal for resource-constrained consumer environments, such as smart devices, Internet of Things (IoT) systems, and mobile platforms. Finally, an experimental investigation on radio frequency fingerprinting for consumer devices is conducted using an AI-driven model called TinyMLP, and our model achieves ≈ 97% authentication accuracy by resisting adversarial attacks.

Publication Type:	Article
Additional Information:	© 2026 IEEE. This accepted manuscript is made available under the terms of the Creative Commons Attribution License (CC-BY), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited.
Publisher Keywords:	Consumer applications, adversarial machine learning attacks, post-quantum authentication, key agreement, security
Subjects:	H Social Sciences > HD Industries. Land use. Labor H Social Sciences > HN Social history and conditions. Social problems. Social reform Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology School of Science & Technology > Department of Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads