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

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.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16372
Primary Topic
Quantum Information and Cryptography
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

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

Ramon Jose C. Bagunu
arXiv (Cornell University)
Quantum Information and Cryptography
preprint

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

Ramon Jose C. Bagunu
preprint en

Abstract

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 (Cornell University)
Quantum Information and Cryptography
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon