Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

EEG Authentication System Based on One- and Multi-Class Machine Learning Classifiers

  • Hernández-Álvarez, Luis
  • Barbierato, Elena
  • Caputo, Stefano
  • Mucchi, Lorenzo
  • Hernández Encinas, Luis
19 páginas, 10 tablas, 3 figuras, In the current Information Age, it is usual to access our personal and professional information, such as bank account data or private documents, in a telematic manner. To ensure the privacy of this information, user authentication systems should be accurately developed. In this work, we focus on biometric authentication, as it depends on the user's inherent characteristics and, therefore, offers personalized authentication systems. Specifically, we propose an electrocardiogram (EEG)-based user authentication system by employing One-Class and Multi-Class Machine Learning classifiers. In this sense, the main novelty of this article is the introduction of Isolation Forest and Local Outlier Factor classifiers as new tools for user authentication and the investigation of their suitability with EEG data. Additionally, we identify the EEG channels and brainwaves with greater contribution to the authentication and compare them with the traditional dimensionality reduction techniques, Principal Component Analysis, and $\chi^2$ statistical test. In our final proposal, we elaborate on a hybrid system resistant to random forgery attacks \color{black} using an Isolation Forest and a Random Forest classifiers, obtaining a final accuracy of $82.3\%$, a precision of $91.1\%$ and a recall of $75.3\%$., This research was funded by the Spanish State Research Agency (AEI) of the Ministry of Sci- ence and Innovation (MCIN), project P2QProMeTe Grant No. PID2020-112586RBI00/AEI/10.13039/ 50110001103. This work was supported in part by Comunidad de Madrid (Spain) through Project CYNAMON, Grant No. P2018/TCS-4566-CM, co-funded by the European Regional Develop- ment Fund (ESF, FEDER and ERDF, EU); in part by the European Union’s Horizon 2020 Research and Innovation Program under Grant No. 872752 and under Grant No. 101017141; in part by the European Telecommunication Standard Institute (ETSI) technical committee (TC) on Smart Body Area Network (SmartBAN). L.H.-Á. would like to thank CSIC Project CASDiM for its support. E.B would like to thank UNICESV (Centro Universitario Di Ricerca Per Lo Sviluppo Competitivo Del Settore Vitivinicolo).
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Post-Quantum Wireless-Based Key Encapsulation Mechanism via CRYSTALS-Kyber for Resource-Constrained Devices

  • González de la Torre, M.A.
  • Morales Sandoval, I.A.
  • Freitas de Abreu, Giuseppe Thadeu
  • Hernández Encinas, Luis
11 páginas, 5 figuras, 7 tablas, We consider the problem of adapting a Post-Quantum cryptosystem to be used in resource-constrained devices, such as those typically used in Device-to-Device and Internet of Things systems. In particular, we propose leveraging the characteristics of wireless communications channels to minimize the complexity of implementation of a Post-Quantum public key encryption scheme, without diminishing its security. To that end, we focus on the adaptation of a well-known cryptosystem, namely CRYSTALS-Kyber, so as to enable its direct integration into the lowest layer of the communication stack, the physical layer, defining two new transport schemes for CRYSTALS-Kyber to be used in Device-to-Device communications, both of which are modeled under a wireless channel subject to Additive White Gaussian Noise, using a 4 Quadrature Amplitude Modulation constellation and a BCH-code to communicate CRYSTALS-Kyber's polynomial coefficients. Simulation results demonstrate the viability of the adapted Kyber algorithm due to its low key error probability, while maintaining the security reductions of the original Kyber by considering the error distribution imposed by the channel on the cipher., This work was supported in part by European Union (EU)-Japan European interest Group (EiG)-Concert Project Organically Resilient and Secure Wireless Networks for Next-Generation IoT Technologies to serve Future Connected Societies (ORACLE), Germany, under Grant 01DR21011; in part by EU-Japan EiG-Concert Project ORACLE, Spain, funded by MCIN/AEI/10.13039/501100011033 and EU ‘‘NextGenerationEU’’/Plan de Recuperación, Transformación y Resiliencia (PRTR) under Grant PCI2020-120691-2; in part by Project P2QProMeTe funded by MCIN/AEI/10.13039/501100011033 under Grant PID2020-112586RBI00; and in part by Project Quantum-based Resistant Architectures and Techniques Integration QKD+PQC (QURSA) funded by MCIN/AEI/10.13039/501100011033 co-funded by EU ‘‘NextGenerationEU’’/PRTR under Grant TED2021-130369B-C33., Peer reviewed