Repositorio Institucional
Repositorio Institucional
CONICET Digital
  • Inicio
  • EXPLORAR
    • AUTORES
    • DISCIPLINAS
    • COMUNIDADES
  • Estadísticas
  • Novedades
    • Noticias
    • Boletines
  • Ayuda
    • General
    • Datos de investigación
  • Acerca de
    • CONICET Digital
    • Equipo
    • Red Federal
  • Contacto
JavaScript is disabled for your browser. Some features of this site may not work without it.
  • INFORMACIÓN GENERAL
  • RESUMEN
  • ESTADISTICAS
 
Artículo

The HEIC application framework for implementing XAI-based socio-technical systems

Paredes, José NicolásIcon ; Teze, Juan Carlos LionelIcon ; Martinez, Maria VaninaIcon ; Simari, GerardoIcon
Fecha de publicación: 11/2022
Editorial: Elsevier
Revista: Online Social Networks and Media
e-ISSN: 2468-6964
Idioma: Inglés
Tipo de recurso: Artículo publicado
Clasificación temática:
Ciencias de la Computación

Resumen

The development of data-driven Artificial Intelligence systems has seen successful application in diverse domains related to social platforms; however, many of these systems cannot explain the rationale behind their decisions. This is a major drawback, especially in critical domains such as those related to cybersecurity, of which malicious behavior on social platforms is a clear example. In light of this problem, in this paper we make several contributions: (i) a proposal of desiderata for the explanation of outputs generated by AI-based cybersecurity systems; (ii) a review of approaches in the literature on Explainable AI (XAI) under the lens of both our desiderata and further dimensions that are typically used for examining XAI approaches; (iii) the Hybrid Explainable and Interpretable Cybersecurity (HEIC) application framework that can serve as a roadmap for guiding R&D efforts towards XAI-based socio-technical systems; (iv) an example instantiation of the proposed framework in a news recommendation setting, where a portion of news articles are assumed to be fake news; and (v) exploration of various types of explanations that can help different kinds of users to identify real vs. fake news in social platform settings.
Palabras clave: APPLICATION FRAMEWORKS , CYBERSECURITY , EXPLAINABLE AND INTERPRETABLE ARTIFICIAL INTELLIGENCE , HYBRID AI , MALICIOUS BEHAVIOR IN SOCIAL NETWORKS , NEWS RECOMMENDER SYSTEMS
Ver el registro completo
 
Archivos asociados
Tamaño: 3.414Mb
Formato: PDF
.
Solicitar
Licencia
info:eu-repo/semantics/restrictedAccess Excepto donde se diga explícitamente, este item se publica bajo la siguiente descripción: Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Unported (CC BY-NC-SA 2.5)
Identificadores
URI: http://hdl.handle.net/11336/204876
URL: https://www.sciencedirect.com/science/article/abs/pii/S2468696422000416
DOI: https://doi.org/10.1016/j.osnem.2022.100239
Colecciones
Articulos(SEDE CENTRAL)
Articulos de SEDE CENTRAL
Citación
Paredes, José Nicolás; Teze, Juan Carlos Lionel; Martinez, Maria Vanina; Simari, Gerardo; The HEIC application framework for implementing XAI-based socio-technical systems; Elsevier; Online Social Networks and Media; 32; 11-2022; 1-20
Compartir
Altmétricas
 

Enviar por e-mail
Separar cada destinatario (hasta 5) con punto y coma.
  • Facebook
  • X Conicet Digital
  • Instagram
  • YouTube
  • Sound Cloud
  • LinkedIn

Los contenidos del CONICET están licenciados bajo Creative Commons Reconocimiento 2.5 Argentina License

https://www.conicet.gov.ar/ - CONICET

Inicio

Explorar

  • Autores
  • Disciplinas
  • Comunidades

Estadísticas

Novedades

  • Noticias
  • Boletines

Ayuda

Acerca de

  • CONICET Digital
  • Equipo
  • Red Federal

Contacto

Godoy Cruz 2290 (C1425FQB) CABA – República Argentina – Tel: +5411 4899-5400 repositorio@conicet.gov.ar
TÉRMINOS Y CONDICIONES