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

International Conference on Smart Applications, Communications and Networking (SmartNets)

Adaptive Quantum-Classical Cryptographic Selection: An RL-Based Architecture for DN25

Darlan Noetzold, Jorge L. V. Barbosa, Juan F. De Paz, Valderi Reis Quietinho Leithardt

Published Jul 7, 2026• 0 citations
Publisher

Abstract

We present Q-OPSEC, an adaptive middleware that uses supervised, unsupervised and reinforcement learning to select cryptographic strategies from classical, post-quantum and quantum-assisted (QKD) options. The selection is modeled as a multi-objective MDP that balances security, latency, computational and energy cost, and compliance. A negotiator and registry enforce hard constraints, handle endpoint compatibility and fallbacks, and store empirical cost profiles. Experiments in simulated smart environments and hardware-in-the-loop tests show high success rates ($>95 \%$) and context-aware adaptation. Limitations include reliance on simulated QKD channels, limited device profiling, empirically tuned hyperparameters, and evaluation in high-performance environments, which may not reflect IoT constraints; future work targets real QKD integration, broader benchmarking, robust RL methods, federated learning and explainability.

DOI
10.1109/smartnets69662.2026.11604688

Related papers

Q-OPSEC: An Architecture Proposal for Adaptive AI Middleware for Quantum Cryptography

Darlan Noetzold, Jorge L. V. Barbosa, Juan F. P. Santana +1 more

Q-OPSEC is a proposed adaptive middleware architecture that integrates the strengths of the Oraculum and PRISEC models, now enhanced with quantum cryptography. Leveraging artificial intelligence-including supervised, unsupervised, and reinforcement learning-Q-OPSEC autonomously analyzes contextual information and dynamically selects crypto-graphic strategies. The architecture incorporates both classical and quantum-safe methods, such as Quantum Key Distribution (QKD) and post-quantum cryptographic (PQC) algorithms, to address current and emerging security threats. Designed as a plug-and-play solution for heterogeneous IoT and smart environments, Q-OPSEC adapts encryption strength and security policies in real time based on risk assessment and system context, aiming to fill critical gaps in context-aware and future-oriented data protection.

International Conference on Electrical and Computer Engineering Researches (ICECER)•Dec 6, 2025•3 citations

Reinforcement Learning-Based Adaptive Quantum-Safe Cryptography for DN25-Compliant Smart Environments

Darlan Noetzold, Jorge L. V. Barbosa, Juan F. De Paz +1 more

The emergence of quantum computing challenges traditional security mechanisms, particularly in heterogeneous and resource-constrained IoT and smart environments that must satisfy DN25 requirements. This work introduces a reinforcement learning-driven model for the adaptive selection and orchestration of cryptographic algorithms. Acting as an intelligent decision layer, the system observes contextual, network, and operational metrics to recommend or enforce configurations combining classical schemes, post-quantum cryptography, and Quantum Key Distribution when available. The selection problem is formulated as a Markov Decision Process with state and action spaces aligned with protocol control flows and is embedded into a security middleware with negotiation and fallback mechanisms to ensure interoperability and policy compliance without modifying application logic. Experimental results demonstrate that the model dynamically adjusts key lengths, algorithm families, and security policies according to risk and resource conditions, increasing post-quantum cryptography and Quantum Key Distribution usage by up to 33.4% and 23.9% in high-risk scenarios while favoring low-latency classical or hybrid options for less critical traffic. The system achieves success rates above 78% while maintaining stable latency and resource usage during extended operation.

IEEE Access•Jan 1, 2026•7 citations

Adaptive Quantum-Classical Hybrid Authentication: Dynamic Protocol Switching for Real-Time Threat Mitigation

Abrar Galib Zaman, Montasir Qasymeh

Quantum computing is a threat to the existence of classical cryptographic authentication. Although quantum key distribution (QKD) has quantitative security, its real-life implementation is interfered with due to two reasons: the resource scalability and the availability of an authenticated classical channel. The presented paper proposes a new system, termed as Adaptive Hybrid Authentication Framework (AHAF), as a solution to these issues as it switches dynamically between classical, post-quantum, and quantum authentication protocols. An AHAF is based on a Reinforcement Learning (RL) based decision engine that transforms the problem of protocol selection into a Markov Decision Process (MDP). A multi-objective reward function is maximised by the RL agent, where the security posture, resources consumption in the system and performance are balanced according to real-time threats intelligence and resource availability. The AHAF was structured and verified in some high-fidelity simulation environment that incorporates NetSquid and NS-3. The findings clarify that the AHAF system is a capable solution that prevents a variety of simulated threats and meets the hypothesis of expected uptime (99.9 percent). This is achieved by carefully assigning expensive quantum protocols on a need-to-use basis and so providing QKD level of protection without incurring prohibitive performance cost of a fixed implementation. We have determined that an RL-based learning strategy most readily delivers workable and competitive road map towards feasible quantum-safe communication networks.

•Jun 24, 2025•1 citation

AI-Driven Quantum Cryptography: Machine Learning for Robust QKD, Secure Operations, and Quantum-Safe Integration

Ankit Gupta, Shilpi Mittal

Quantum Key Distribution (QKD) provides key exchange security grounded in quantum physics, but practical deployments still face constraints in scalability, noise tolerance, real-time operations, and implementation security. In parallel, machine learning (ML) has proven effective for adaptive control, prediction, and anomaly detection in complex cyber-physical systems. This paper reviews how AI/ML can be integrated into QKD to improve robustness and operational security without weakening core cryptographic guarantees. We present an AI-supported QKD architecture, summarize key performance metrics (QBER, secret key rate, and throughput), and outline how learning-based control can tune parameters dynamically under varying channel conditions. We also discuss security-operations integration (SOC visibility, alerting, and key lifecycle telemetry) and provide a reinforcement learning (RL) case study to illustrate adaptive parameter selection. Finally, we analyze threats introduced by AI and identify practical design constraints (fail-safe behavior, policy bounds, and verification) required to preserve quantum-security principles while enabling quantum-safe integration with post-quantum cryptography workflows.

IEEE International Conference on AI in Cybersecurity (ICAIC)•Feb 18, 2026•1 citation

Quantum-Aware Reinforcement Learning Framework for Adaptive Quantum Key Distribution

Palisetty Rudrabhishek, Medikonda Mahathi Anushma, Pallapothu Moulika +1 more

Quantum technology is revolutionizing communication networks, which are guaranteed to be secure through Quantum Key Distribution (QKD). Classical cryptography relies on the assumption that certain computational problems are hard, and QKD offers information-theoretic security based on the laws of quantum physics. Nevertheless, a practical realization is challenging. Photon loss, environmental noise, and time-varying channel conditions can all significantly reduce the secure key generation rate . Standard QKD protocols are based on fixed parameters and passive loss compensation, and thus, are not capable of modulating network conditions in real time. In this paper, we propose a Quantum-Aware Reinforcement Learning Framework (QARLF). This is a combined AI-QKD architecture for self-learning, adaptive and predictive quantum networks. Our scheme consists of a Quantum Channel Sensor Layer that continuously monitors the channel conditions, a Reinforcement Learning (RL) Agent that learns to predict the optimal system parameters, and an Adaptive Control Unit (ACU) that conducts real-time adaptation. The RL agent is trained to employ a quantum-adaptive reward function considering the growth of the secure key rate, the reduction of the quantum bit error rate (QBER), and the operational cost. The agent uses Q-learning with a Boltzmann exploration strategy to progressively enhance its policy. The results demonstrate that QARLF can track channel variations effectively and adapt parameters in real time. It significantly boosts the secure key rates over the conventional static or reactive approach. This is a step towards self-adapting, quantum-savvy networks.

IEEE International Conference on Recent Advances in Electronics, Communication, Computing, Automation and Power (RECCAP)•May 1, 2026•0 citations

Adaptive Quantum Cryptography: A Dynamic Security Framework for Future IoT Networks

M. Thillai, K. Durga, Bharathi Ramesh +2 more

The rapid proliferation of Internet of Things (IoT) devices presents critical cybersecurity challenges, as traditional cryptographic methods often fail to provide both robust security and operational efficiency in resource-constrained environments. This paper introduces Adaptive Quantum Cryptography (AQC), a novel framework designed to secure next-generation IoT networks against evolving classical and quantum-computing threats. The AQC framework synergistically integrates Quantum Key Distribution (QKD) for unbreakable key exchange, Quantum Random Number Generators (QRNGs) for high-entropy key generation, and Post-Quantum Cryptography (PQC) for quantum-resistant data encryption. A key feature of the system is its dynamic adaptation mechanism, which leverages artificial intelligence to intelligently select and adjust cryptographic protocols in real-time based on current network conditions, device computational capabilities, and identified threat levels. This ensures optimal security without imposing excessive overhead on IoT devices. Our comprehensive experimental evaluation demonstrates that the AQC framework significantly outperforms classical techniques, achieving a 70% improvement in key exchange efficiency, a 50% reduction in computational load, and a 95% resilience rate against quantum-based attacks. By providing forward secrecy and robust authentication, the proposed AQC framework offers a scalable, energy-efficient, and future-proof security solution, paving the way for resilient and trustworthy IoT ecosystems in the post-quantum era.

CompSci & AI Advances•Apr 13, 2026•0 citations
We present Q-OPSEC, an adaptive middleware that uses supervised, unsupervised and reinforcement learning to select cryptographic strategies from classical, post-quantum and quantum-assisted (QKD) options. The selection is modeled as a multi-objective MDP that balances security, latency, computational and energy cost, and compliance. A negotiator and registry enforce hard constraints, handle endpoint compatibility and fallbacks, and store empirical cost profiles. Experiments in simulated smart environments and hardware-in-the-loop tests show high success rates (>95%>95 \%>95%) and context-aware adaptation. Limitations include reliance on simulated QKD channels, limited device profiling, empirically tuned hyperparameters, and evaluation in high-performance environments, which may not reflect IoT constraints; future work targets real QKD integration, broader benchmarking, robust RL methods, federated learning and explainability.
Q-OPSEC is a proposed adaptive middleware architecture that integrates the strengths of the Oraculum and PRISEC models, now enhanced with quantum cryptography. Leveraging artificial intelligence-including supervised, unsupervised, and reinforcement learning-Q-OPSEC autonomously analyzes contextual information and dynamically selects crypto-graphic strategies. The architecture incorporates both classical and quantum-safe methods, such as Quantum Key Distribution (QKD) and post-quantum cryptographic (PQC) algorithms, to address current and emerging security threats. Designed as a plug-and-play solution for heterogeneous IoT and smart environments, Q-OPSEC adapts encryption strength and security policies in real time based on risk assessment and system context, aiming to fill critical gaps in context-aware and future-oriented data protection.
The emergence of quantum computing challenges traditional security mechanisms, particularly in heterogeneous and resource-constrained IoT and smart environments that must satisfy DN25 requirements. This work introduces a reinforcement learning-driven model for the adaptive selection and orchestration of cryptographic algorithms. Acting as an intelligent decision layer, the system observes contextual, network, and operational metrics to recommend or enforce configurations combining classical schemes, post-quantum cryptography, and Quantum Key Distribution when available. The selection problem is formulated as a Markov Decision Process with state and action spaces aligned with protocol control flows and is embedded into a security middleware with negotiation and fallback mechanisms to ensure interoperability and policy compliance without modifying application logic. Experimental results demonstrate that the model dynamically adjusts key lengths, algorithm families, and security policies according to risk and resource conditions, increasing post-quantum cryptography and Quantum Key Distribution usage by up to 33.4% and 23.9% in high-risk scenarios while favoring low-latency classical or hybrid options for less critical traffic. The system achieves success rates above 78% while maintaining stable latency and resource usage during extended operation.
Quantum computing is a threat to the existence of classical cryptographic authentication. Although quantum key distribution (QKD) has quantitative security, its real-life implementation is interfered with due to two reasons: the resource scalability and the availability of an authenticated classical channel. The presented paper proposes a new system, termed as Adaptive Hybrid Authentication Framework (AHAF), as a solution to these issues as it switches dynamically between classical, post-quantum, and quantum authentication protocols. An AHAF is based on a Reinforcement Learning (RL) based decision engine that transforms the problem of protocol selection into a Markov Decision Process (MDP). A multi-objective reward function is maximised by the RL agent, where the security posture, resources consumption in the system and performance are balanced according to real-time threats intelligence and resource availability. The AHAF was structured and verified in some high-fidelity simulation environment that incorporates NetSquid and NS-3. The findings clarify that the AHAF system is a capable solution that prevents a variety of simulated threats and meets the hypothesis of expected uptime (99.9 percent). This is achieved by carefully assigning expensive quantum protocols on a need-to-use basis and so providing QKD level of protection without incurring prohibitive performance cost of a fixed implementation. We have determined that an RL-based learning strategy most readily delivers workable and competitive road map towards feasible quantum-safe communication networks.
Quantum Key Distribution (QKD) provides key exchange security grounded in quantum physics, but practical deployments still face constraints in scalability, noise tolerance, real-time operations, and implementation security. In parallel, machine learning (ML) has proven effective for adaptive control, prediction, and anomaly detection in complex cyber-physical systems. This paper reviews how AI/ML can be integrated into QKD to improve robustness and operational security without weakening core cryptographic guarantees. We present an AI-supported QKD architecture, summarize key performance metrics (QBER, secret key rate, and throughput), and outline how learning-based control can tune parameters dynamically under varying channel conditions. We also discuss security-operations integration (SOC visibility, alerting, and key lifecycle telemetry) and provide a reinforcement learning (RL) case study to illustrate adaptive parameter selection. Finally, we analyze threats introduced by AI and identify practical design constraints (fail-safe behavior, policy bounds, and verification) required to preserve quantum-security principles while enabling quantum-safe integration with post-quantum cryptography workflows.
Quantum technology is revolutionizing communication networks, which are guaranteed to be secure through Quantum Key Distribution (QKD). Classical cryptography relies on the assumption that certain computational problems are hard, and QKD offers information-theoretic security based on the laws of quantum physics. Nevertheless, a practical realization is challenging. Photon loss, environmental noise, and time-varying channel conditions can all significantly reduce the secure key generation rate . Standard QKD protocols are based on fixed parameters and passive loss compensation, and thus, are not capable of modulating network conditions in real time. In this paper, we propose a Quantum-Aware Reinforcement Learning Framework (QARLF). This is a combined AI-QKD architecture for self-learning, adaptive and predictive quantum networks. Our scheme consists of a Quantum Channel Sensor Layer that continuously monitors the channel conditions, a Reinforcement Learning (RL) Agent that learns to predict the optimal system parameters, and an Adaptive Control Unit (ACU) that conducts real-time adaptation. The RL agent is trained to employ a quantum-adaptive reward function considering the growth of the secure key rate, the reduction of the quantum bit error rate (QBER), and the operational cost. The agent uses Q-learning with a Boltzmann exploration strategy to progressively enhance its policy. The results demonstrate that QARLF can track channel variations effectively and adapt parameters in real time. It significantly boosts the secure key rates over the conventional static or reactive approach. This is a step towards self-adapting, quantum-savvy networks.
The rapid proliferation of Internet of Things (IoT) devices presents critical cybersecurity challenges, as traditional cryptographic methods often fail to provide both robust security and operational efficiency in resource-constrained environments. This paper introduces Adaptive Quantum Cryptography (AQC), a novel framework designed to secure next-generation IoT networks against evolving classical and quantum-computing threats. The AQC framework synergistically integrates Quantum Key Distribution (QKD) for unbreakable key exchange, Quantum Random Number Generators (QRNGs) for high-entropy key generation, and Post-Quantum Cryptography (PQC) for quantum-resistant data encryption. A key feature of the system is its dynamic adaptation mechanism, which leverages artificial intelligence to intelligently select and adjust cryptographic protocols in real-time based on current network conditions, device computational capabilities, and identified threat levels. This ensures optimal security without imposing excessive overhead on IoT devices. Our comprehensive experimental evaluation demonstrates that the AQC framework significantly outperforms classical techniques, achieving a 70% improvement in key exchange efficiency, a 50% reduction in computational load, and a 95% resilience rate against quantum-based attacks. By providing forward secrecy and robust authentication, the proposed AQC framework offers a scalable, energy-efficient, and future-proof security solution, paving the way for resilient and trustworthy IoT ecosystems in the post-quantum era.