arXiv:2610.35410
Multimode continuous-variable quantum key distribution with CMOS-compatible photonic-electronic integration
Yiming Bian, Sarah Bastiaens, Saeed Hakimi, Huy Quang Nguyen, Aboobackkar Sidhique, Cédric Bruynsteen, Govind J. Wanjalkar, Ali Al Hadi Amhaz, Jasper Jans, Axl Bomhals, Ulrik L. Andersen, Tobias Gehring, Xin Yin, Adnan A. E. Hajomer
Abstract
Multiplexing and photonic-electronic integration offer a route to scalable and high-throughput quantum key distribution (QKD) networks through parallel transmission and compact hardware suited to volume manufacturing. Realizing this route requires multichannel transmitters and receivers, and a security analysis accounting for mode coupling. Here we present a CMOS-compatible photonic-electronic multimode continuous-variable QKD architecture, using polarization multiplexing as a two-mode example. Silicon-photonic transmitter and receiver chips prepare and detect two polarization modes in parallel. The receiver is co-integrated with a dual-channel 28-nm CMOS transimpedance amplifier, providing shot-noise clearances exceeding 20 dB in both channels. Pilot-assisted unitary digital recovery removes the need for active optical polarization control, while a multimode security analysis accounts for the mode crosstalk. At 2 percent residual crosstalk, the multimode analysis extends the simulated secure distance from 39 to 84 km, near the crosstalk-free limit of 89 km. Over 10 km of deployed fibre, the mean total finite-size secret-key rate estimate is 6.69 Mbit/s, 12 percent above the single-mode analysis from the same digitally recovered data. These results establish a route to scalable multimode quantum-secured networks built on technology suited to mass production.
AI Summary
The paper addresses parallel continuous-variable QKD with integrated hardware when imperfect mode separation leaves crosstalk that single-mode security analyses count as excess noise. It combines silicon-photonic transmitters and receivers, dual-channel 28-nm CMOS electronic readout, unitary digital polarization recovery, and a multimode security analysis. For each receiver mode, the analysis retains correlations with all independently prepared, trusted source modes while conservatively assigning other receiver modes to Eve. Gaussian covariance matrices bound Eve’s Holevo information under collective attacks; finite-size parameter estimation uses multivariate regression confidence regions and a numerical worst-case search. Reconciliation still uses only the intended source–receiver pair. Distinguishable pilots estimate polarization mixing, whose nearest unitary matrix is inverted digitally rather than using active optical polarization control. The two-polarization receiver achieves over 20 dB shot-noise clearance in both channels across approximately 0.1–1 GHz. Over 10 km of deployed fibre, at 125 MBaud per polarization, ten measurement rounds yield a mean total finite-size secret-key rate estimate of 6.69 Mbit/s, versus 5.97 Mbit/s from single-mode analysis of the same recovered data—a 12% increase. Simulations with ideal detectors and 2% residual crosstalk extend estimated secure reach from 39 to 84 km, compared with 89 km without crosstalk. Error correction and privacy amplification are not executed, and composable security remains future work. The experiment uses shared-clock, co-located endpoints and external optical components. Detection efficiency is 0.334, primarily limited by coupling; higher-mode finite-size penalties and worst-case-search scaling remain unquantified.
Central claim may not hold: The reported finite-size security against collective attacks relies on confidence regions proved only for Gaussian regression residuals, an additional restriction not supplied by Gaussian optimality of the Holevo bound. The numerical search reports a worst-case candidate without demonstrating that its Holevo information upper-bounds the entire permitted confidence region, leaving the security conservativeness of the reported rates unverified.
Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.