Skip to content

GCRI · Inteligencia artificial y sistemas autónomos

Ciberseguridad de la IA

AI and cybersecurity meet in three ways: AI sistemas can be attacked, AI can help attackers, and AI can help defenders. Models can be poisoned, stolen, manipulated or made to leak data; their supply chains of data, weights and libraries carry new risks. This page sets out how these threats work, how AI systems are secured, and what evidence serves the security teams and regulators responsible.

01Registro

AI cyber security on the record.

02La pregunta

AI cyber security: how the risk develops.

Adversarial methods and model exposure. The dossier below sets out how the risk develops, what is measured, where the data come from, how it is modelled and who decides.

Mecanismo

Models are attack surfaces

Adversarial inputs, prompt injection, data extraction and model theft target the model itself. Classic application vulnerabilities still apply around it.

Mecanismo

The AI supply chain is long

Training data, pretrained weights, libraries and plugins come from many sources. Poisoned data or tampered models can introduce hidden behaviour.

Mecanismo

AI lowers the cost of some attacks

Generative AI can draft phishing, translate lures and help write code, lowering the skill barrier for some attacks. The size of this effect is studied and debated.

Mecanismo

AI assists defence

Machine learning detects anomalies, triages alerts and finds vulnerabilities. Defenders must also secure the AI tools they adopt.

03Simulador

Una cascada a través de redes interdependientes.

A huella de amenaza elimina los activos colocalizados en cada capa; la fragmentación, la dependencia entre capas y la sobrecarga de los supervivientes propagan después el fallo. La vista 3D separa las capas por profundidad. Modelo didáctico con valores ilustrativos declarados, no una predicción.

Controles

Activos por capa
18
Huella de la amenaza
8 % de la superficie
Activos que dependen de otra capa
60%
Capacidad de reserva (tolerancia)
30%

Lecturas

Activos afectados por la amenaza
7%
Activos que siguen funcionando
50%
Amplificación del daño inicial
6.8 times
Pasos hasta la liquidación
3
Cifras, métodos y fuentes
PasoCentros de datos en funcionamiento (%)Redes en funcionamiento (%)Funcionamiento eléctrico (%)
08394100
1727894
2616750
3616722

Métodos

  1. Redes interdependientes Buldyrev and others (2010), Catastrophic cascade of failures in interdependent networks, Nature 464
  2. Cascadas de sobrecarga Motter and Lai (2002), Physical Review E 66
  3. Carga de intermediación Brandes (2001), Journal of Mathematical Sociology 25
  4. Redes multicapa Kivela and others (2014), Journal of Complex Networks 2
  5. Interdependencias de infraestructuras Rinaldi, Peerenboom and Kelly (2001), IEEE Control Systems 21(6)
  6. Abanico de incertidumbre (Monte Carlo de parámetros) Spiegelhalter, Pearson y Short (2011), Visualising uncertainty about the future, Science 333
  7. Sensibilidad de un factor a la vez (tornado) Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley

Datos

The model runs on the teaching values set by the controls. To calibrate it for a place, read it against these admitted layers and series, which this page’s map can draw:

  • Carreteras principales Natural Earth
  • Ferrocarriles Natural Earth
  • Puertos marítimos Natural Earth
  • Aeropuertos Natural Earth
  • Extensiones urbanas Natural Earth
  • Luces nocturnas esta noche, cortes (banda día/noche VIIRS) NASA/NOAA VIIRS (Suomi NPP) · registro nasa.gibs.context-live-layers
  • Eventos naturales (NASA EONET) NASA EONET · registro nasa.eonet.events
Una cascada a través de redes interdependientes. Modelo didáctico ilustrativo: funciona con los valores fijados por los controles, no con datos medidos. Métodos: redes interdependientes (Buldyrev y otros (2010), Catastrophic cascade of failures in interdependent networks, Nature 464); cascadas de sobrecarga (Motter y Lai (2002), Physical Review E 66); carga de intermediación (Brandes (2001), Journal of Mathematical Sociology 25).
04En todos los dominios

AI changes cyber risk in every domain’s control systems.

05Métodos y evidencia

How AI cyber security is modelled, measured and tested.

El modelo, sus supuestos, sus datos y su incertidumbre, en la forma en que un científico o un ingeniero los comprobaría. Las estructuras siguen métodos publicados. Los valores representados son ilustrativos, no hallazgos.

Modelo de sistema

The couplings between the systems in AI cyber security: signs of influence, a reinforcing and a balancing loop, and cross-links where stress jumps.

++−+Inteligencia artificialDatosComunidadesEconomíaR de refuerzoB equilibrio
Causal loop diagram from the page’s systems; signs show the direction of influence. Illustrative structure for a system dynamics or network model, not estimated couplings.
Principios rectores FAIR · GO FAIR y FORCE11W3C PROV · World Wide Web ConsortiumOrientación para un tratamiento coherente de las incertidumbres · IPCCCEOS Analysis Ready Data · Comité sobre Satélites de Observación de la Tierra
06Indicadores

Qué se mide y con qué calidad.

Cada indicador lleva su unidad, su periodicidad, el tipo de fuente que lo respalda y la etiqueta de evidencia que llevaría un valor. No se muestran valores: un programa los aporta bajo su propia autoridad.

IndicadorUnidadCadenciaTipo de fuenteEtiqueta
Vulnerabilities reported in AI frameworks and librariescount of CVE entriesmensualVulnerability databasesNOTIFICADO
Adversarial robustnessaccuracy under a stated attackper evaluationRobustness testingOBSERVADO
Models with signed provenancepercent of deployed modelsper inventoryModel registriesDECLARADO
AI-related security incidentscount by techniqueanualIncident reportsNOTIFICADO
Time to detect AI system compromisehoursper incidentIncident response recordsOBSERVADO
Organisations with AI security policiespercent of surveyed organisationsper surveyIndustry surveysNOTIFICADO
07Fuentes

De dónde procede la evidencia.

Conjuntos de datos públicos y registros institucionales identificados, cada uno con su tipo de licencia. Las fuentes obtenidas por acuerdo solo se utilizan conforme a sus condiciones y nunca se republican.

FuenteLo que aportaTipo de licencia
MITRE ATLASAdversarial tactics and techniques against AI sistemas, with case studiesPublic, licence to check
NIST adversarial machine learning taxonomyTerminology and taxonomy of attacks and mitigationsPublic domain, US government
National Vulnerability Database and CVE recordsVulnerabilities in AI softwarePublic domain, US government
ENISA reports on AI cybersecurityThreat landscape and good practice for securing AIPublic, ENISA terms
Joint guidance from national cyber agencies on secure AI system developmentSecure design, development, deployment and operationPublic, terms per agency
08Decisiones

Quién decide y a qué sirve la evidencia.

Estudio de Inteligencia artificial y sistemas prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

Quién decideLa preguntaEvidencia a la que sirve esta página
Chief information security officersHow to secure AI systems the organisation builds or buysThreat models; supply chain checklists
National cybersecurity agenciesWhat guidance to issue on AI securityIncident and vulnerability evidence
DesarrolladoresWhich defences to build into models and applicationsRobustness testing; attack taxonomies

Productos que genera este tema

  • Threat models for AI deployments
  • AI supply chain security checklists
  • Robustness testing protocols
  • Evidence notes on AI-enabled attack trends
09Cuestiones centrales

What security researchers ask.

  • How can inputs be crafted to make a model misbehave, and how robust are defences?
  • Can an attacker poison training data or tamper with model weights in the supply chain?
  • Can private training data or a model itself be extracted through its outputs?
  • How does AI change attackers’ and defenders’ capabilities?
10Mecanismos

The AI attack surface.

Adversarial examples are inputs altered in ways imperceptible to people that cause models to err. Data poisoning inserts malicious examples into training data to plant backdoors. Membership inference and extraction attacks recover information about training data or replicate a model through repeated queries. For language models, jailbreaks and prompt injection bypass intended restrictions.

On the other side, AI can help attackers find vulnerabilities, write malware variants and craft convincing phishing at scale, and help defenders triage alerts, analyse code and detect anomalies. The balance between the two is an open research question.

11Métodos y datos

Security engineering for AI.

  1. 01

    Red-teaming

    Structured attempts to break a system, combining ciberseguridad y criptografía and artificial intelligence and machine learning expertise. Red-teaming finds problems but cannot prove their absence.

  2. 02

    Threat modelling

    Mapping assets, adversaries and attack paths across data, training, deployment and supply chain.

  3. 03

    Robustness testing

    Measuring performance under adversarial perturbation. Robustness to known attacks does not imply robustness to new ones.

  4. 04

    Supply-chain integrity

    Provenance of datasets, models and dependencies, with signing and verification. Provenance tooling is still maturing.

13Where this page’s references

Where this page’s references lead.

Los organismos y documentos con los que se lee esta página. El estado y las ediciones cambian; cada enlace lleva al organismo emisor.

14Preguntas

Preguntas y respuestas.

What is data poisoning?
Manipulating training data so that a model learns hidden behaviours or performs worse, for example responding to a trigger in a way the attacker chooses.
What is MITRE ATLAS?
A knowledge base of adversary tactics and techniques against AI systems, modelled on MITRE ATT&CK, with real-world case studies.
Does AI make cyberattacks easier?
It can lower the effort for some tasks, such as writing phishing messages, according to agency assessments. How much it changes overall attack capability is still being studied.
Does the platform publish attack techniques?
Only at a level that supports defence, following responsible disclosure. Details that would mainly enable harm are not published.
How do I report a vulnerability?
Escribir a el formulario de informes de seguridad. El acuse de recibo proporciona una referencia e indica el siguiente paso.
Is open release of model weights a security risk?
It is a trade-off. Open weights enable scrutiny, research and local control, and also make misuse and the removal of safeguards easier. The balance depends on the model’s capabilities.
Can AI defend against AI-enabled attacks?
It can help, but it is not a complete answer. Basic security practices, monitoring and human expertise remain essential.
serie ReportsContribuir

Aporte evidencia desde esta página.

serie Reports is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.

GCRIInteligencia artificial y sistemas autónomosTecnología exponencialEvidencia de Labs
Inteligencia artificial y sistemas autónomos

Aporte un método, un conjunto de datos o una pregunta.

La información y las consultas están abiertas hoy. Una consulta recibe una referencia e indica el siguiente paso; las solicitudes, pagos, asignaciones de cómputo y registros solo se abren cuando existen su equipo, sus condiciones y la capacidad de revisión.