Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

A Survey of Quantum-Proofing LLMs and Agentic AI: Security Threats, Post-Quantum Cryptography, and Open Challenges

Mehran Mozaffari Kermani

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.2139/ssrn.7576261

Related papers

REVIEW ON ARTIFICIAL INTELLIGENCE ON POST QUANTUM CRYPTOGRAPHY FOR SECURE COMMUNICATION

Vidhumitha a

Indo Asian Journal of Management and Entrepreneurship•Nov 29, 2024•0 citations

A Survey of Quantum-Proofing LLMs and Agentic AI: Security Threats, Post-Quantum Cryptography, and Open Challenges

Mehran Mozaffari Kermani

This survey examines the security of LLM systems and agentic artificial intelligence (AI) from a quantum-threat perspective.Rather than providing another general survey of LLM attacks, we focus on the emerging intersection of LLM security, quantumcomputing, and post-quantum cryptography (PQC).

•Oct 10, 2026•0 citations

Exploring the Security Implications of Quantum Computing on Current Encryption Techniques

Sandeep Dommari

•Jan 1, 2025•0 citations

Post-Quantum Cryptography and Blockchain Framework for Secure AI-RAN in 6G Networks

Pasindu Udugahapattuwa, Chamitha De Alwis, Engin Zeydan +2 more

Artificial Intelligence-driven Radio Access Networks (AI-RAN) are a core paradigm of 6G, but the tight coupling of AI models, open interfaces, and distributed control loops raises security and trust challenges that cryptographically relevant quantum computers worsen by breaking the public-key cryptography underpinning current AI-RAN security. Existing work treats post-quantum cryptography (PQC), blockchain, and AI-RAN security as disjoint problems, leaving a gap at their intersection. This paper addresses that gap with a structured synthesis and an architectural framework that integrates latticebased PQC and a permissioned blockchain into the O-RAN control plane for quantum-resistant identity management, AI model integrity, policy enforcement, and trust orchestration. The contribution is an integration and enforcement design, not a new primitive: an AI-RAN-specific quantum threat mapping and an enforcement model that keeps blockchain consensus off the Near-RT RIC hot path via cached attestation tokens and hierarchical verification. A feasibility analysis grounded in surveyed ML-DSA/ML-KEM micro-benchmarks bounds the design envelope, and limitations, notably the gap between surveyed componentlevel numbers and integrated end-to-end performance, are stated explicitly.

International Conference on Future and Intelligent Networking (FINE)•Aug 1, 2026•0 citations

Categorical Framework for Quantum-Resistant Zero-Trust AI Security

I. Cherkaoui, C. Clarke, J. Horgan +1 more

The rapid deployment of AI models necessitates robust, quantum-resistant security, particularly against adversarial threats. Here, we present a novel integration of post-quantum cryptography (PQC) and zero trust architecture (ZTA), formally grounded in category theory, to secure AI model access. Our framework uniquely models cryptographic workflows as morphisms and trust policies as functors, enabling fine-grained, adaptive trust and micro-segmentation for lattice-based PQC primitives. This approach offers enhanced protection against adversarial AI threats. We demonstrate its efficacy through a concrete ESP32-based implementation, validating a crypto-agile transition with quantifiable performance and security improvements, underpinned by categorical proofs for AI security. The implementation achieves significant memory efficiency on ESP32, with the agent utilizing 91.86% and the broker 97.88% of free heap after cryptographic operations, and successfully rejects 100% of unauthorized access attempts with sub-millisecond average latency.

cs.CRCross-listedarXiv:2511.21768•Nov 26, 2025

Quantum Computing and AI Revolutionizing Cryptography and Security

Utpal Chakraborty

COJ Robotics & Artificial Intelligence•Feb 16, 2022•0 citations
Artificial Intelligence-driven Radio Access Networks (AI-RAN) are a core paradigm of 6G, but the tight coupling of AI models, open interfaces, and distributed control loops raises security and trust challenges that cryptographically relevant quantum computers worsen by breaking the public-key cryptography underpinning current AI-RAN security. Existing work treats post-quantum cryptography (PQC), blockchain, and AI-RAN security as disjoint problems, leaving a gap at their intersection. This paper addresses that gap with a structured synthesis and an architectural framework that integrates latticebased PQC and a permissioned blockchain into the O-RAN control plane for quantum-resistant identity management, AI model integrity, policy enforcement, and trust orchestration. The contribution is an integration and enforcement design, not a new primitive: an AI-RAN-specific quantum threat mapping and an enforcement model that keeps blockchain consensus off the Near-RT RIC hot path via cached attestation tokens and hierarchical verification. A feasibility analysis grounded in surveyed ML-DSA/ML-KEM micro-benchmarks bounds the design envelope, and limitations, notably the gap between surveyed componentlevel numbers and integrated end-to-end performance, are stated explicitly.
The rapid deployment of AI models necessitates robust, quantum-resistant security, particularly against adversarial threats. Here, we present a novel integration of post-quantum cryptography (PQC) and zero trust architecture (ZTA), formally grounded in category theory, to secure AI model access. Our framework uniquely models cryptographic workflows as morphisms and trust policies as functors, enabling fine-grained, adaptive trust and micro-segmentation for lattice-based PQC primitives. This approach offers enhanced protection against adversarial AI threats. We demonstrate its efficacy through a concrete ESP32-based implementation, validating a crypto-agile transition with quantifiable performance and security improvements, underpinned by categorical proofs for AI security. The implementation achieves significant memory efficiency on ESP32, with the agent utilizing 91.86% and the broker 97.88% of free heap after cryptographic operations, and successfully rejects 100% of unauthorized access attempts with sub-millisecond average latency.