Predicting optimal parameters with random forest for quantum key distribution

For practical quantum key distribution (QKD) in finite-data case, full optimized parameters can greatly improve its key rate. To gain such optimal parameters, traditional search algorithms are performed quite frequently despite the high time and hardware overhead, which may be a severe challenge for real-time QKD systems and large-scale QKD networks. In this paper, instead of searching optimal parameters, we employ random forest to directly predict those parameters. Firstly, we illustrate the feasibility of this method with 3-intensity measurement-device-independent QKD (MDI-QKD). Later, we rebuild a versatile model applicable to MDI and BB84 protocol simultaneously. Both numerical simulations demonstrate our method enjoys a low time and hardware overhead compared with traditional search method and achieves over 99% of the optimal secure key rate as well, which is very promising in future QKD applications.

[1]  Xiang‐Bin Wang,et al.  Three-intensity decoy-state method for device-independent quantum key distribution with basis-dependent errors , 2012, 1207.0392.

[2]  Lo,et al.  Unconditional security of quantum key distribution over arbitrarily long distances , 1999, Science.

[3]  Zoubin Ghahramani,et al.  The Random Forest Kernel and other kernels for big data from random partitions , 2014, ArXiv.

[4]  Won-Young Hwang.  Quantum key distribution with high loss: toward global secure communication. , 2003, Physical review letters.

[5]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[6]  Xiongfeng Ma,et al.  ar X iv : q ua ntp h / 05 12 08 0 v 2 1 1 A pr 2 00 6 TIMESHIFT ATTACK IN PRACTICAL QUANTUM , 2005 .

[7]  H. Lo,et al.  Practical decoy state for quantum key distribution (15 pages) , 2005 .

[8]  H. Lo,et al.  Practical Decoy State for Quantum Key Distribution , 2005, quant-ph/0503005.

[9]  Xiongfeng Ma,et al.  Decoy state quantum key distribution. , 2004, Physical review letters.

[10]  James F. Dynes,et al.  A quantum access network , 2013, Nature.

[11]  Hoi-Kwong Lo,et al.  Machine learning for optimal parameter prediction in quantum key distribution , 2018, Physical Review A.

[12]  Gilles Brassard,et al.  Quantum cryptography: Public key distribution and coin tossing , 2014, Theor. Comput. Sci..

[13]  N. Lutkenhaus,et al.  Quantum key distribution with realistic states: photon-number statistics in the photon-number splitting attack , 2001, quant-ph/0112147.

[14]  Stefano Pirandola,et al.  Side-channel-free quantum key distribution. , 2011, Physical review letters.

[15]  Dominic Mayers,et al.  Unconditional security in quantum cryptography , 1998, JACM.

[16]  N. Lütkenhaus.  Security against individual attacks for realistic quantum key distribution , 2000 .

[17]  Shor,et al.  Simple proof of security of the BB84 quantum key distribution protocol , 2000, Physical review letters.

[18]  Feihu Xu,et al.  Protocol choice and parameter optimization in decoy-state measurement-device-independent quantum key distribution , 2014, 1406.0188.

[19]  Feihu Xu,et al.  Concise security bounds for practical decoy-state quantum key distribution , 2013, 1311.7129.

[20]  Yang Liu,et al.  Measurement-device-independent quantum key distribution over untrustful metropolitan network , 2015, 1509.08389.

[21]  Sanders,et al.  Limitations on practical quantum cryptography , 2000, Physical review letters.

[22]  Wei Cui,et al.  Finite-key analysis for measurement-device-independent quantum key distribution , 2013, Nature Communications.

[23]  Dag R. Hjelme,et al.  Faked states attack on quantum cryptosystems , 2005 .

[24]  Xiaolong Hu,et al.  Efficient measurement-device-independent quantum key distribution without vacuum sources , 2017 .

[25]  Xiang‐Bin Wang,et al.  Beating the PNS attack in practical quantum cryptography , 2004 .

[26]  Shuang Wang,et al.  Parameter optimization and real-time calibration of a measurement-device-independent quantum key distribution network based on a back propagation artificial neural network , 2018, Journal of the Optical Society of America B.

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  Y.-H. Zhou,et al.  Making the decoy-state measurement-device-independent quantum key distribution practically useful , 2015, 1502.01262.

[29]  M. Curty,et al.  Measurement-device-independent quantum key distribution. , 2011, Physical review letters.

[30]  Nicolai Meinshausen,et al.  Quantile Regression Forests , 2006, J. Mach. Learn. Res..