{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:13:18Z","timestamp":1760231598320,"version":"build-2065373602"},"reference-count":36,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Vlatacom Institute of High Technologies","award":["#164 EEG_Keys"],"award-info":[{"award-number":["#164 EEG_Keys"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>It is well known that Renyi\u2019s entropy of order 2 determines the maximum possible length of the distilled secret keys in sequential secret key distillation protocols so that no information is leaked to the eavesdropper. There have been no attempts to estimate this key quantity based on information available to the legitimate parties to this protocol in the literature. We propose a new machine learning system, which estimates the lower bound of conditional Renyi entropy with high accuracy, based on 13 characteristics locally measured on the side of legitimate participants. The system is based on a prediction intervals deep neural network, trained for a given source of common randomness. We experimentally evaluated this result for two different sources, namely 14 and 6-dimensional EEG signals, of 50 participants, with varying advantage distillation and information reconciliation strategies with and without additional lossless compression block. Across all proposed systems and analyzed sources on average, the best machine learning strategy, called the hybrid strategy, increases the quantity of generated keys 2.77 times compared to the classical strategy. By introducing the Huffman lossless coder before the PA block, the loss of potential source randomness was reduced from 68.48% to a negligible 0.75%, while the leakage rate per one bit remains in the order of magnitude 10\u22124.<\/jats:p>","DOI":"10.3390\/sym14102028","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T01:23:16Z","timestamp":1664414596000},"page":"2028","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Privacy Amplification Strategies in Sequential Secret Key Distillation Protocols Based on Machine Learning"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-5730","authenticated-orcid":false,"given":"Jelica","family":"Radomirovi\u0107","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Belgrade University, Bulevar kralja Aleksandra 73, 11120 Belgrade, Serbia"},{"name":"Vlatacom Institute of High Technology, Milutina Milankovica 5, 11070 Belgrade, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milan","family":"Milosavljevi\u0107","sequence":"additional","affiliation":[{"name":"Vlatacom Institute of High Technology, Milutina Milankovica 5, 11070 Belgrade, Serbia"},{"name":"Technical Faculty, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Branko","family":"Kova\u010devi\u0107","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Belgrade University, Bulevar kralja Aleksandra 73, 11120 Belgrade, Serbia"},{"name":"Vlatacom Institute of High Technology, Milutina Milankovica 5, 11070 Belgrade, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milo\u0161","family":"Jovanovi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Information Technologies, Belgrade Metropolitan University, Tadeu\u0161a Ko\u0161\u0107u\u0161ka 63, 11000 Belgrade, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1002\/j.1538-7305.1949.tb00928.x","article-title":"Communication Theory of Secrecy Systems","volume":"28","author":"Shannon","year":"1949","journal-title":"Bell Syst. Tech. J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/3-540-48969-X_10","article-title":"Unconditional Security in Cryptography","volume":"Volume 1561","author":"Wolf","year":"1998","journal-title":"Lectures on Data Security: Modern Cryptology in Theory and Practice, Lecture Notes in Computer Science"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1109\/18.243431","article-title":"Common randomness in information theory and cryptography, Part I: Secret sharing","volume":"39","author":"Ahlswede","year":"1993","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1109\/18.256484","article-title":"Secret key agreement by public discussion from common information","volume":"39","author":"Maurer","year":"1993","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3047","DOI":"10.1109\/TIT.2004.838380","article-title":"Secrecy Capacities for Multiple Terminals","volume":"50","author":"Csiszar","year":"2004","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Galis, M., Milosavljevi\u0107, M., Jevremovi\u0107, A., Banjac, Z., Makarov, A., and Radomirovi\u0107, J. (2021). Secret-Key Agreement by Asynchronous EEG over Authenticated Public Channels. Entropy, 23.","DOI":"10.37247\/ETNI2ED.2.22.4"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/18.476316","article-title":"Generalized privacy amplification","volume":"41","author":"Bennett","year":"1995","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1007\/3-540-39799-X_37","article-title":"How to reduce your enemy\u2019s information","volume":"Volume 218","author":"Bennett","year":"1986","journal-title":"Advances in Cryptology, Proceedings of Crypto \u201985, Lecture Notes in Computer Science"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1137\/0217014","article-title":"Privacy Amplification by Public Discussion","volume":"17","author":"Bennett","year":"1988","journal-title":"SIAM J. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1109\/ACCESS.2016.2521718","article-title":"Key Generation from Wireless Channels: A Review","volume":"4","author":"Zhang","year":"2016","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Impagliazzo, R., Levin, L.A., and Michael, L. (1989, January 14\u201317). Pseudo-random Generation from one-way functions. Proceedings of the 21st Annual ACM Symposium on Theory of Computing, Seattle, WA, USA.","DOI":"10.1145\/73007.73009"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Guglielmi, A.V., Muraro, A., Cisotto, G., and Laurenti, N. (2021, January 7\u201311). Information Theoretic Key Agreement Protocol based on ECG signals. Proceedings of the IEEE Global Communications Conference (GLOBECOM), Madrid, Spain.","DOI":"10.1109\/GLOBECOM46510.2021.9685523"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3023954","article-title":"Gait-Key: A gait-based shared secret key generation protocol for wearable devices","volume":"13","author":"Xu","year":"2017","journal-title":"ACM Trans. Sen. Netw."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3022","DOI":"10.1109\/TCOMM.2018.2814607","article-title":"High-Agreement Uncorrelated Secret Key Generation Based on Principal Component Analysis Preprocessing","volume":"66","author":"Li","year":"2018","journal-title":"IEEE Trans. Commun."},{"key":"ref_15","unstructured":"NIST (2021, October 06). A Statistical Test Suite for Random and Pseudorandom Number Generators for Cryptographic Applications, Available online: https:\/\/csrc.nist.gov\/publications\/detail\/sp\/800-22\/rev-1a\/final."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2389","DOI":"10.1109\/COMST.2018.2812301","article-title":"Information and Communications Technologies for Sustainable Development Goals: State-of-the-Art, Needs and Perspectives","volume":"20","author":"Wu","year":"2018","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ma, B., Wu, J., Lai, E., and Hu, S. (2021, January 7\u201311). PPDTSA: Privacy-preserving Deep Transformation Self-attention Framework For Object Detection. Proceedings of the IEEE Global Communications Conference (GLOBECOM), Madrid, Spain.","DOI":"10.1109\/GLOBECOM46510.2021.9685855"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1109\/TIT.2003.809559","article-title":"Secret-key agreement over unauthenticated public channels\u2014Part III. Privacy amplification","volume":"49","author":"Maurer","year":"2003","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_19","unstructured":"Yakovlev, V., Korzhik, V.I., Morales-Luna, G.B., and Bakaev, M. (2010). Key distribution protocols based on extractors under the condition of noisy channels in the presence of an active adversary. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/0022-0000(79)90044-8","article-title":"Universal classes of hash functions","volume":"18","author":"Carter","year":"1979","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bloch, M., and Barros, J. (2011). Physical-Layer Security: From Information Theory to Security Engineering, Cambridge University Press.","DOI":"10.1017\/CBO9780511977985"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"54033","DOI":"10.1109\/ACCESS.2018.2871713","article-title":"Calibrated Prediction Intervals for Neural Network Regressors","volume":"6","author":"Keren","year":"2018","journal-title":"IEEE Access"},{"key":"ref_23","unstructured":"Kivaranovic, D., Johnson, K., and Leeb, H. (2020, January 26\u201328). Adaptive, Distribution\/Free Prediction Intervals for Deep Networks. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Palermo, Italy."},{"key":"ref_24","unstructured":"Simhayev, E., Katz, G., and Rokach, L. (2020). PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TNN.2010.2096824","article-title":"Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals","volume":"22","author":"Khosravi","year":"2010","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_26","unstructured":"(2022, August 06). Elisim\/PIVEN-GitHub. Available online: https:\/\/github.com\/elisim\/piven."},{"key":"ref_27","unstructured":"(2021, October 06). Emotiv|Brain Data Measuring Hardware and Software Solutions. Available online: http:\/\/emotiv.com."},{"key":"ref_28","unstructured":"(2022, August 06). Emotiv|EpocX. Available online: https:\/\/www.emotiv.com\/epoc-x\/."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1002\/sec.1192","article-title":"Analysis of the information theoretically secret key agreement by public discussion","volume":"8","author":"Wang","year":"2015","journal-title":"Secur. Commun. Netw."},{"key":"ref_30","first-page":"410","article-title":"Secret key reconciliation by public discussion","volume":"Volume 765","author":"Brassard","year":"1994","journal-title":"Advances in Cryptology\u2014EUROCRYPT\u201993"},{"key":"ref_31","unstructured":"Reis, A. (2019). Quantum Key Distribution Post Processing\u2014A Study on the Information Reconciliation Cascade Protocol. [Master\u2019s Thesis, Faculdade de Engenharia, Universidade do Porto]."},{"key":"ref_32","unstructured":"(2021, October 06). Brunorijsman\/Cascade-Python\u2014GitHub. Available online: https:\/\/github.com\/brunorijsman\/cascade-python."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"052303","DOI":"10.1103\/PhysRevA.67.052303","article-title":"Fast, efficient error reconciliation for quantum cryptography","volume":"67","author":"Buttler","year":"2003","journal-title":"Phys. Rev. A"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1109\/JRPROC.1952.273898","article-title":"A Method for the Construction of Minimum-Redundancy Codes","volume":"40","author":"Huffman","year":"1952","journal-title":"Proc. IRE"},{"key":"ref_35","unstructured":"Gander, M.J., and Maurer, U.M. (1994, January 20\u201324). On the secret key rate of binary random variables. Proceedings of the 1994 International Symposium on Information Theory and Its applications, Sydney, Australia."},{"key":"ref_36","unstructured":"(2022, May 01). Keras API. Available online: https:\/\/keras.io\/api\/utils\/model_plotting_utils\/#plot_model-function."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/10\/2028\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:40:32Z","timestamp":1760143232000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/10\/2028"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["sym14102028"],"URL":"https:\/\/doi.org\/10.3390\/sym14102028","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2022,9,27]]}}}