• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer
  • Facebook
  • Instagram
  • LinkedIn
  • TikTok
  • Twitter
  • YouTube
CDE Almería – Centro de Documentación Europea – Universidad de Almería

CDE Almería - Centro de Documentación Europea - Universidad de Almería

Centro de Documentación Europea de la Universidad de Almería

  • HOME
  • WHAT´S ON
    • EU BULLETINS
    • EU NEWS
    • Activities
    • EU Calls and Awards
    • Radio Program «Europe with You»
  • DOCUMENTATION
    • Bibliographic Collection
      • Almería EDC Digital Collection
      • UNIVERSITY OF ALMERIA LIBRARY
    • Documentation by topic
    • EU Media Collection
      • Web Space
      • MEDIATHEQUE REPOSITORY
  • Europe on the net
    • Institutions
    • EU Representation in Spain
    • European information network of Andalusia
    • EU official journal
  • ABOUT US
    • Presentation
    • People
    • Contact
  • English
  • Spanish

Artificial Intelligence: How to make Machine Learning Cyber Secure?

Inicio » Noticias UE » Defensa y Seguridad » Cybersecurity » Artificial Intelligence: How to make Machine Learning Cyber Secure?

20 de December de 2021

How to prevent machine learning cyberattacks? How to deploy controls without hampering performance? The European Union Agency for Cybersecurity answers the cybersecurity questions of machine learning.

Machine learning (ML) is currently the most developed and the most promising subfield of artificial intelligence for industrial and government infrastructures. By providing new opportunities to solve decision-making problems intelligently and automatically, artificial intelligence (AI) is applied in almost all sectors of our economy.

While the benefits of AI are significant and undeniable, the development of AI also induces new threats and challenges, identified in the ENISA AI Threat Landscape.

Machine learning algorithms are used to give machines the ability to learn from data in order to solve tasks without being explicitly programmed to do so. However, such algorithms need extremely large volumes of data to learn. And because they do, they can also be subjected to specific cyber threats.

The Securing Machine Learning Algorithms report presents a taxonomy of ML techniques and core functionalities. The report also includes a mapping of the threats targeting ML techniques and the vulnerabilities of ML algorithms. It provides a list of relevant security controls recommended to enhance cybersecurity in systems relying on ML techniques. One of the challenges highlighted is how to select the security controls to apply without jeopardising the expected level of performance.

The mitigation controls for ML specific attacks outlined in the report should in general be deployed during the entire lifecycle of systems and applications making use of ML.

Machine Learning Algorithms Taxonomy

Based on desk research and interviews with the experts of the ENISA AI ad-hoc working group, a total of 40 most commonly used ML algorithms were identified. The taxonomy developed is based on the analysis of such algorithms.

The non-exhaustive taxonomy devised is to support the process of identifying which specific threats target ML algorithms, what are the associated vulnerabilities and the security controls needed to address those vulnerabilities.

Target audience

  • Public/government: EU institutions & agencies, regulatory bodies of Member States, supervisory authorities in data protection, military and intelligence agencies, law enforcement community, international organisations and national cybersecurity authorities.
  • Industry at large including small & medium enterprises (SMEs) resorting to AI solutions, operators of essential services ;
  • AI technical, academic and research community, AI cybersecurity experts and AI experts such as designers, developers, ML experts, data scientists, etc.
  • Standardisation bodies.

More information

Press release – ENISA

Publicaciones relacionadas:

cyber-security-EU-ENISAENISA: Cyber Attacks Becoming More Sophisticated Default ThumbnailPhishing most common Cyber Incident faced by SMEs European Cybersecurity MonthEuropean Cybersecurity Month cyber-security singaporeENTRUSTED: The EU’s new security project Latest cyber-attacks on the EU

“This is a space for debate. All comments, for or against publication, that are respectful and do not contain expressions that are discriminatory, defamatory or contrary to current legislation will be published”.

Reader Interactions

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Primary Sidebar

Publicaciones relacionadas


cyber-security-EU-ENISAENISA: Cyber Attacks Becoming More Sophisticated


Default ThumbnailPhishing most common Cyber Incident faced by SMEs


European Cybersecurity MonthEuropean Cybersecurity Month


cyber-security singaporeENTRUSTED: The EU’s new security project


Latest cyber-attacks on the EU

Footer

Logotipo en negativo del Centro de Documentación Europea de Almería
  • CDE Almería
  • Edificio Parque Científico-Tecnológico (Pita)
  • Planta: 1ª, Despacho: 2904120.
  • Ctra. Sacramento s/n. Almería (Spain)
  • Teléfono: (+34) 950 015266

HOME
NEWS
DOCUMENTATION
EUROPE ON THE NET
ABOUT US

  • LEGAL NOTICE
  • PRIVACY POLICY
  • COOKIE POLICY
  • ACCESSIBILITY
  • SITEMAP

Copyright © 2023 CDE Almería · Creative Commons LicenseThis work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

<p>El Centro de Documentación Europea de la Universidad de Almería utiliza cookies propias y de terceros para facilitar al usuario la navegación en su página Web y el acceso a los distintos contenidos alojados en la misma. Asimismo, se utilizan cookies analíticas de terceros para medir la interacción de los usuarios con el sitio Web. Pinche el siguiente enlace si desea información sobre el uso de cookies y como deshabilitarlas. ajustes</p>

Politica de privacidad

El Centro de Documentación Europea de la Universidad de Almería utiliza cookies propias y de terceros para facilitar al usuario la navegación en su página Web y el acceso a los distintos contenidos alojados en la misma. Asimismo, se utilizan cookies analíticas de terceros para medir la interacción de los usuarios con el sitio Web. Pinche el siguiente enlace si desea información sobre el uso de cookies y como deshabilitarlas. <a href="/politica-de-cookies" rel="noopener" target="_blank">Más información</a>

Cookies estrictamente necesarias

Las cookies estrictamente necesarias tiene que activarse siempre para que podamos guardar tus preferencias de ajustes de cookies.

Básicamente la web no funcionara bien si no las activas.

Estas cookies son:

  • Comprobación de inicio de sesión.
  • Cookies de seguridad.
  • Aceptación/rechazo previo de cookies.

Si desactivas esta cookie no podremos guardar tus preferencias. Esto significa que cada vez que visites esta web tendrás que activar o desactivar las cookies de nuevo.

Cookies de terceros

Esta web utiliza Google Analytics, Google Tag Manager y Yandex Metrika para recopilar información anónima tal como el número de visitantes del sitio, o las páginas más populares.

Dejar estas cookies activas nos permite mejorar nuestra web.

¡Por favor, activa primero las cookies estrictamente necesarias para que podamos guardar tus preferencias!

Política de cookies

Pinche el siguiente enlace si desea información sobre el uso de cookies y como deshabilitarlas. Más información