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

arXiv:2606.22962 · Quantum Information Processing

Adversarial Reinforcement Learning for Adaptive Eavesdropping in BB84 Quantum Key Distribution

Ramon Jose C. Bagunu

quant-phSubmitted Jun 22, 2026• Announced Jun 23, 2026• 4 citations
arXivHTMLPDF

Abstract

BB84 quantum key distribution derives its security from a physical guarantee that any eavesdropper disturbs the channel in a statistically detectable way. Prior work evaluates this by assuming Eve attacks at a fixed, analytically optimized rate. We examine what happens when Eve is modeled instead as a learning agent. Classical reinforcement learning is used, specifically tabular Q-Learning, SARSA, and Double Q-Learning, to adaptive BB84 eavesdropping. This formulates the attacker's decision as a Markov Decision Process where the agent observes Quantum Bit Error Rate (QBER) feedback and decides, qubit by qubit, whether to intercept or pass. Experiments span three channel noise levels ($μ_{ch}\in\{1\%,3\%,5\%\}$) and are validated across five independent random seeds (45 training runs per condition, 10,000 episodes each). Against the best non-adaptive analytical baseline, Q-Learning reduces detection from $99.4\%$ to $0.28\%\pm0.27\%$ at $μ_{ch}=1\%$ while extracting approximately 10.5 correct bits per episode. This is a 355-fold reduction that is statistically significant ($p=0.020$, Mann-Whitney $U$ test). We also report the spontaneous emergence of an end-game burst, where agents independently learn to surge their attack rate at the final block. This exploit vanishes under randomized checkpoint intervals while stealth performance remains statistically indistinguishable. These results motivate the inclusion of adaptive adversary baselines in quantum cryptographic security evaluations.

Comments
8 pages, 8 figures, 3 tables

Related papers

No Convergence in Learned Eavesdropping-Detection Dynamics for BB84 Quantum Key Distribution

Ramon Jose C. Bagunu

In prior work we showed that a reinforcement-learning eavesdropper can intercept BB84 quantum key distribution while holding the quantum bit error rate below the abort threshold and keeping a usable distillable key. In this paper we ask whether an equally adaptive learning detector can close this stealth window. We cast the interaction as an alternating best-response game between a tabular eavesdropper and a tabular threshold-adapting detector. We measure exploitability, which is the detection rate and distillable key fraction achieved by a fresh attacker best-responding to the final detector. Across three learning rules (Q-Learning, SARSA, Double Q-Learning), three channel-noise levels, and a uniform false-alarm discipline, the dynamics do not settle out to twenty rounds. The exploitability does not approach a fixed point, and its round-to-round swings do not decay. Two controls, one retraining the attacker against a frozen defender and one retraining the defender against a frozen attacker, show that the swings on each side match the variance of the best-response procedure itself. The dynamics fluctuate at the scale of best-response variance rather than converging, with neither player settling to a fixed response. The behavior is noise-dependent, and the stealth window stays open at the low noise where practical QKD operates. The defender contains the attacker on average at intermediate noise without the contest settling, and at high noise the channel rather than the learned policy suppresses the attack. As a candidate mechanism we examine a last-mover information asymmetry, supported by significant anti-persistence at intermediate noise and consistent with best-response noise at low noise. The results suggest that a learned detector cannot be certified from any single round, and that closing the window calls for breaking the information structure rather than out-adapting the attacker.

arXiv:2611.16372•Nov 12, 2026•0 citations

MARL-Driven Adaptive Defense for PracticalBB84 QKD under Adversarial Conditions

Prince Kumar, P Akhila, Shashidhar G. Koolagudi

Abstract We present a game-theoretic reinforcement learning framework for analyzing adversarial behavior in BB84 quantum key distribution (QKD). Unlike traditional security proofs that assume a worst-case eavesdropper, our approach models an adaptive attacker and corresponding defensive strategies. We develop a fast analytical QKD simulator capturing key metrics such as gain, Quantum Bit Error Rate (QBER), decoy-state statistics, and multiple attack types including intercept-resend, photon-number splitting, time-shift, and dark-count attacks. The interaction between Bob and an adaptive eavesdropper Eve is formulated as a repeated zero-sum game and trained using deep reinforcement learning. Eve learns to maximize information gain while remaining stealthy, whereas Bob learns counter- measures that minimize information leakage while preserving secret key rate (SKR). Experimental results show an emergent arms race, where Bob reduces Eve’s achievable information by nearly 50% while maintaining practical SKR, leading to a stable equilibrium. This work demonstrates that reinforcement learning is a pow- erful tool for exploring adaptive security in QKD and provides a foundation for studying more realistic adversarial scenarios in quantum communication systems.

•Jun 3, 2026•0 citations

Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift

Marcel Mordarski, Benjamin Gras, Abdelrahman Shehata +2 more

Quantum key distribution (QKD) links are provisioned from security analyses of stationary channels, whereas the devices that determine the channel drift between recalibrations. Whether an eavesdropper who cannot alter the channel's own noise gains by following that drift has not been quantified. Adaptive eavesdropping is posed here as a constrained Markov decision process in which the attacker selects one circuit per round while the noise level follows an Ornstein--Uhlenbeck process and the abort condition is a budget over each block of rounds. The value of adaptation is bounded by the best fixed circuit and a dynamic-programming upper bound. The actions are learnt attacks. Whereas Decker et al. trained a parametrised circuit on a fixed gate template against a fixed channel, here the gate structure and rotation angles are searched jointly. This yields circuits compact enough to form a discrete action set, extending the construction to noise models lacking a known template, including the amplitude damping channel. On device-independent E91 under bilateral depolarising noise, a reinforcement-learning attacker raises her Holevo information from $0.135$ for the best fixed circuit to $0.348$ at zero detection, $98\%$ of the upper bound. On BB84 under a drifting bit-flip channel, she exceeds a conservative noise-indexed rule by $0.024$ in fidelity, reaching $99\%$ of the upper bound. Under stationary noise, the attacker's gain from basis asymmetry changes sign between an averaged and a per-basis error-rate constraint. The search, started from random gate sequences, recovers the analytical cloners and the collective-attack key rate, and meets the lower bound of the Winick--Lütkenhaus--Coles objective from above.

quant-pharXiv:2610.01792•Oct 2, 2026•0 citations

Reinforcement Learning-based Adaptive Error Correction for BB84 Quantum Key Distribution: A Q-Learning Approach to Post-Processing Optimization

Devishree Rohit Naidu, Sweta Jain, Ananya Anand +2 more

In Quantum Key Distribution (QKD) protocol BB84, a crucial step is post-processing. It is where the communicating parties correct errors caused either by channel noise or by an eavesdropper. Standard BB84 implementations usually relies on fixed choices of post-processing parameters. This often leads to extra classical communication and lowers the effective key generation rate. In this work, we propose an adaptive framework based on reinforcement learning that changes the error-correction block size dynamically during the classical reconciliation stage of BB84. We have tested this idea using Qiskit Aer simulations over 200 runs with key lengths ranging from 100 to 500 qubits. Here we observed approximately 30-50% reduction in communication overhead compared to the conventional fixed-block settings. Even though this introduces slightly higher error rates, it still improves the overall efficiency of key generation across all evaluated key sizes. This indicates that reinforcement learning can make QKD post-processing more efficient. This can open opportunities for quantum-secure communication systems.

International Conference on Connected Intelligence for Industrial Applications (CI2A)•Apr 3, 2026•0 citations

Quantum Bit Error Rate Analysis in BB84 Quantum Key Distribution: Measurement, Statistical Estimation, and Eavesdropping Detection

Jaydeep Rath, Prajwal Panth, P. S. N. Bhaskar

Quantum Key Distribution (QKD) provides information-theoretic security by exploiting the principles of quantum mechanics. Among QKD protocols, the BB84 scheme remains the most widely adopted for both theoretical research and practical implementation. A critical parameter determining the reliability and security of BB84 is the Quantum Bit Error Rate (QBER), which quantifies errors in the sifted key arising from channel noise or potential eavesdropping. This paper presents a systematic review and analysis of QBER within the BB84 protocol, examining its calculation, statistical estimation methods, and role in detecting eavesdropping activity. Simulation results, corroborated by reported experimental observations, reveal a near-linear relationship between eavesdropping intensity and QBER, with values approaching 25% under full intercept-resend attacks. Four confidence interval estimation methods, Wald, Wilson, Clopper-Pearson, and Hoeffding's inequality, are compared for robust QBER analysis in finite-key scenarios. Protocol enhancements, including decoy-state methods, hybrid cryptographic models, and quantum-resistant authentication, are discussed as mechanisms to mitigate errors and strengthen resilience across fiber, free-space, underwater, and satellite QKD systems. Open challenges in distinguishing noise-induced errors from malicious eavesdropping, and the role of adaptive error correction and machine-learning-assisted QBER estimation in future quantum networks, are identified as key directions for further research.

quant-pharXiv:2603.27278•Mar 31, 2026•1 citation

Adaptive BB84 Quantum Key Distribution Framework: A Comprehensive Implementation and Analysis Platform

Momin Shiraz Shafi, Vivek Parashar Pandey, Momin Rayyan +3 more

With the rapid development of quantum computing, traditional encryption techniques are expected to face serious security challenges in the near future. By depending on the principles of quantum physics rather than computing complexity, Quantum Key Distribution (QKD), and specifically the BB84 protocol, provides a radically new method of secure communication. In this project, an adaptive BB84-based framework is implemented and analyzed under realistic conditions, including channel noise and multiple eavesdropping strategies. The system integrates error correction, privacy amplification, finite-key analysis, and decoy-state mechanisms to reflect practical deployment scenarios. Three major attack models—intercept-resend, photon number splitting, and Trojan horse—are simulated to evaluate protocol robustness. The experimental results show that during normal communication the average Quantum Bit Error Rate (QBER) remains close to 3–4%, whereas the presence of active eavesdropping increases the QBER beyond the commonly accepted 11% threshold, resulting in protocol termination. Additional statistical testing under varying noise conditions confirms stable secret key generation and reliable detection of malicious interference. Overall, the proposed framework serves as a comprehensive simulation platform for studying the security behavior of BB84 in controlled experimental environments.

IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET)•Sep 1, 2026•0 citations
BB84 quantum key distribution derives its security from a physical guarantee that any eavesdropper disturbs the channel in a statistically detectable way. Prior work evaluates this by assuming Eve attacks at a fixed, analytically optimized rate. We examine what happens when Eve is modeled instead as a learning agent. Classical reinforcement learning is used, specifically tabular Q-Learning, SARSA, and Double Q-Learning, to adaptive BB84 eavesdropping. This formulates the attacker's decision as a Markov Decision Process where the agent observes Quantum Bit Error Rate (QBER) feedback and decides, qubit by qubit, whether to intercept or pass. Experiments span three channel noise levels (μch∈{1%,3%,5%}μ_{ch}\in\{1\%,3\%,5\%\}μch​∈{1%,3%,5%}) and are validated across five independent random seeds (45 training runs per condition, 10,000 episodes each). Against the best non-adaptive analytical baseline, Q-Learning reduces detection from 99.4%99.4\%99.4% to 0.28%±0.27%0.28\%\pm0.27\%0.28%±0.27% at μch=1%μ_{ch}=1\%μch​=1% while extracting approximately 10.5 correct bits per episode. This is a 355-fold reduction that is statistically significant (p=0.020p=0.020p=0.020, Mann-Whitney UUU test). We also report the spontaneous emergence of an end-game burst, where agents independently learn to surge their attack rate at the final block. This exploit vanishes under randomized checkpoint intervals while stealth performance remains statistically indistinguishable. These results motivate the inclusion of adaptive adversary baselines in quantum cryptographic security evaluations.
In prior work we showed that a reinforcement-learning eavesdropper can intercept BB84 quantum key distribution while holding the quantum bit error rate below the abort threshold and keeping a usable distillable key. In this paper we ask whether an equally adaptive learning detector can close this stealth window. We cast the interaction as an alternating best-response game between a tabular eavesdropper and a tabular threshold-adapting detector. We measure exploitability, which is the detection rate and distillable key fraction achieved by a fresh attacker best-responding to the final detector. Across three learning rules (Q-Learning, SARSA, Double Q-Learning), three channel-noise levels, and a uniform false-alarm discipline, the dynamics do not settle out to twenty rounds. The exploitability does not approach a fixed point, and its round-to-round swings do not decay. Two controls, one retraining the attacker against a frozen defender and one retraining the defender against a frozen attacker, show that the swings on each side match the variance of the best-response procedure itself. The dynamics fluctuate at the scale of best-response variance rather than converging, with neither player settling to a fixed response. The behavior is noise-dependent, and the stealth window stays open at the low noise where practical QKD operates. The defender contains the attacker on average at intermediate noise without the contest settling, and at high noise the channel rather than the learned policy suppresses the attack. As a candidate mechanism we examine a last-mover information asymmetry, supported by significant anti-persistence at intermediate noise and consistent with best-response noise at low noise. The results suggest that a learned detector cannot be certified from any single round, and that closing the window calls for breaking the information structure rather than out-adapting the attacker.
Abstract We present a game-theoretic reinforcement learning framework for analyzing adversarial behavior in BB84 quantum key distribution (QKD). Unlike traditional security proofs that assume a worst-case eavesdropper, our approach models an adaptive attacker and corresponding defensive strategies. We develop a fast analytical QKD simulator capturing key metrics such as gain, Quantum Bit Error Rate (QBER), decoy-state statistics, and multiple attack types including intercept-resend, photon-number splitting, time-shift, and dark-count attacks. The interaction between Bob and an adaptive eavesdropper Eve is formulated as a repeated zero-sum game and trained using deep reinforcement learning. Eve learns to maximize information gain while remaining stealthy, whereas Bob learns counter- measures that minimize information leakage while preserving secret key rate (SKR). Experimental results show an emergent arms race, where Bob reduces Eve’s achievable information by nearly 50% while maintaining practical SKR, leading to a stable equilibrium. This work demonstrates that reinforcement learning is a pow- erful tool for exploring adaptive security in QKD and provides a foundation for studying more realistic adversarial scenarios in quantum communication systems.
Quantum key distribution (QKD) links are provisioned from security analyses of stationary channels, whereas the devices that determine the channel drift between recalibrations. Whether an eavesdropper who cannot alter the channel's own noise gains by following that drift has not been quantified. Adaptive eavesdropping is posed here as a constrained Markov decision process in which the attacker selects one circuit per round while the noise level follows an Ornstein--Uhlenbeck process and the abort condition is a budget over each block of rounds. The value of adaptation is bounded by the best fixed circuit and a dynamic-programming upper bound. The actions are learnt attacks. Whereas Decker et al. trained a parametrised circuit on a fixed gate template against a fixed channel, here the gate structure and rotation angles are searched jointly. This yields circuits compact enough to form a discrete action set, extending the construction to noise models lacking a known template, including the amplitude damping channel. On device-independent E91 under bilateral depolarising noise, a reinforcement-learning attacker raises her Holevo information from 0.1350.1350.135 for the best fixed circuit to 0.3480.3480.348 at zero detection, 98%98\%98% of the upper bound. On BB84 under a drifting bit-flip channel, she exceeds a conservative noise-indexed rule by 0.0240.0240.024 in fidelity, reaching 99%99\%99% of the upper bound. Under stationary noise, the attacker's gain from basis asymmetry changes sign between an averaged and a per-basis error-rate constraint. The search, started from random gate sequences, recovers the analytical cloners and the collective-attack key rate, and meets the lower bound of the Winick--Lütkenhaus--Coles objective from above.
In Quantum Key Distribution (QKD) protocol BB84, a crucial step is post-processing. It is where the communicating parties correct errors caused either by channel noise or by an eavesdropper. Standard BB84 implementations usually relies on fixed choices of post-processing parameters. This often leads to extra classical communication and lowers the effective key generation rate. In this work, we propose an adaptive framework based on reinforcement learning that changes the error-correction block size dynamically during the classical reconciliation stage of BB84. We have tested this idea using Qiskit Aer simulations over 200 runs with key lengths ranging from 100 to 500 qubits. Here we observed approximately 30-50% reduction in communication overhead compared to the conventional fixed-block settings. Even though this introduces slightly higher error rates, it still improves the overall efficiency of key generation across all evaluated key sizes. This indicates that reinforcement learning can make QKD post-processing more efficient. This can open opportunities for quantum-secure communication systems.
Quantum Key Distribution (QKD) provides information-theoretic security by exploiting the principles of quantum mechanics. Among QKD protocols, the BB84 scheme remains the most widely adopted for both theoretical research and practical implementation. A critical parameter determining the reliability and security of BB84 is the Quantum Bit Error Rate (QBER), which quantifies errors in the sifted key arising from channel noise or potential eavesdropping. This paper presents a systematic review and analysis of QBER within the BB84 protocol, examining its calculation, statistical estimation methods, and role in detecting eavesdropping activity. Simulation results, corroborated by reported experimental observations, reveal a near-linear relationship between eavesdropping intensity and QBER, with values approaching 25% under full intercept-resend attacks. Four confidence interval estimation methods, Wald, Wilson, Clopper-Pearson, and Hoeffding's inequality, are compared for robust QBER analysis in finite-key scenarios. Protocol enhancements, including decoy-state methods, hybrid cryptographic models, and quantum-resistant authentication, are discussed as mechanisms to mitigate errors and strengthen resilience across fiber, free-space, underwater, and satellite QKD systems. Open challenges in distinguishing noise-induced errors from malicious eavesdropping, and the role of adaptive error correction and machine-learning-assisted QBER estimation in future quantum networks, are identified as key directions for further research.
With the rapid development of quantum computing, traditional encryption techniques are expected to face serious security challenges in the near future. By depending on the principles of quantum physics rather than computing complexity, Quantum Key Distribution (QKD), and specifically the BB84 protocol, provides a radically new method of secure communication. In this project, an adaptive BB84-based framework is implemented and analyzed under realistic conditions, including channel noise and multiple eavesdropping strategies. The system integrates error correction, privacy amplification, finite-key analysis, and decoy-state mechanisms to reflect practical deployment scenarios. Three major attack models—intercept-resend, photon number splitting, and Trojan horse—are simulated to evaluate protocol robustness. The experimental results show that during normal communication the average Quantum Bit Error Rate (QBER) remains close to 3–4%, whereas the presence of active eavesdropping increases the QBER beyond the commonly accepted 11% threshold, resulting in protocol termination. Additional statistical testing under varying noise conditions confirms stable secret key generation and reliable detection of malicious interference. Overall, the proposed framework serves as a comprehensive simulation platform for studying the security behavior of BB84 in controlled experimental environments.