GCRI · Zîrekiya çêkirî û pergalên xweser
Ewlehiya sîber a AI
AI and cybersecurity meet in three ways: AI pergalan 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.
AI cyber security on the record.
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.
Models are attack surfaces
Adversarial inputs, prompt injection, data extraction and model theft target the model itself. Classic application vulnerabilities still apply around it.
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.
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.
AI assists defence
Machine learning detects anomalies, triages alerts and finds vulnerabilities. Defenders must also secure the AI tools they adopt.
Kaskadeyek di tevahiya torên girêdayî de.
A Şopa metirsîyê hebûnên li heman cihî di her qatê de ji holê radike; perçebûn, girêdayîbûna di navbera qatan de û barkirina zêde ya yên mayî paşê têkçûnê belav dikin. Dîmena 3D qatan bi kûrahiyê ji hev vediqetîne. Modela hînkirinê bi nirxên ronîker ên diyarkirî, ne pêşbînî.
Kontrol
- Mal û milk her qat
- 18
- Metirsî: şop
- 8% ya qadê
- Mal û milkên ku bi qateke din ve girêdayî ne
- 60%
- Kapasîteya zêde (tolerans)
- 30%
Xwendin
- Mal û milkên ku metirsî bandor li wan kiriye
- 7%
- Mal û milkên ku hê dixebitin
- 50%
- Mezinbûna zerara destpêkê
- 6.8 times
- Gavên çareserkirinê
- 3
Jimar, rêbaz û çavkanî
| Gav | Navendên daneyê yên ku dixebitin (%) | Tor yên ku dixebitin (%) | Hêz dixebite (%) |
|---|---|---|---|
| 0 | 83 | 94 | 100 |
| 1 | 72 | 78 | 94 |
| 2 | 61 | 67 | 50 |
| 3 | 61 | 67 | 22 |
Rêbaz
- Torên girêdayî Buldyrev û yên din (2010), Catastrophic cascade of failures in interdependent networks, Nature 464
- Zincîra barkêşiya zêde Motter and Lai (2002), Physical Review E 66
- Barê navbeynkariyê Brandes (2001), Journal of Mathematical Sociology 25
- Torên pirqat Kivela and others (2014), Journal of Complex Networks 2
- Girêdayîbûnên binesazê Rinaldi, Peerenboom and Kelly (2001), IEEE Control Systems 21(6)
- Pankeya nediyarîyê (Monte Carlo ya parametreyan) Spiegelhalter, Pearson and Short (2011), Visualising uncertainty about the future, Science 333
- Hesasiyeta yek-yek (tornado) Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley
Dane
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:
- Rêyên sereke Natural Earth
- Rêhesin Natural Earth
- Benderên behrê Natural Earth
- Balafirgeh Natural Earth
- Dirêjahiyên bajarî Natural Earth
- Ronahiya şevê îşev, qutbûn (VIIRS Day/Night Band) NASA/NOAA VIIRS (Suomi NPP) · register nasa.gibs.context-live-layers
- Bûyerên xwezayî (NASA EONET) NASA EONET · tomar nasa.eonet.events
Li seranserê şeş stûnan, bi pêşengiya Nexus Consortium
- Ceribandin Labs
- Hatiye avakirin di Zîrekiya çêkirî û pergalên xweser li Foundry
- Tê ceribandin li Zîrekiya çêkirî û pergalên xweser li Universe
- Hatiye kodkirin di Dîjîtal, Sîber û AI di Standards de
- Hatiye weşandin di Zîrekiya çêkirî û pergalên xweser li Reports
- Tê de tê dayîn Fakulteya Teknolojî û pergalên dîjîtal di Academy de
AI changes cyber risk in every domain’s control systems.
Findings are designed for the rêzeya Exponential Technology. ISO/IEC 23894 (2023) sets AI risk management guidance; the page publishes no attack techniques.
- Defensive evaluations of AI tools.
- Incident case studies.
How AI cyber security is modelled, measured and tested.
Model, texmînên wî, daneyên wî û nediyariya wî, bi şeweyê ku zanyar an endezyar kontrol bike. Avahî rêbazên weşandî dişopînin. Nirxên hatine xêzkirin nimûneyî ne, ne encam in.
Modela pergalê
The couplings between the systems in AI cyber security: signs of influence, a reinforcing and a balancing loop, and cross-links where stress jumps.
What is measured, and how well.
Each indicator carries its unit, its cadence, the kind of source behind it and the evidence label a value would carry. No values are shown: a programme supplies them under its own authority.
| Indicator | Unit | Cadence | Source type | Nîşan |
|---|---|---|---|---|
| Vulnerabilities reported in AI frameworks and libraries | count of CVE entries | monthly | Vulnerability databases | REPORTED |
| Adversarial robustness | accuracy under a stated attack | per evaluation | Robustness testing | ÇAVDÊRÎKIRÎ |
| Models with signed provenance | percent of deployed models | per inventory | Model registries | DECLARED |
| AI-related security incidents | count by technique | annual | Incident reports | REPORTED |
| Time to detect AI system compromise | hours | per incident | Incident response records | ÇAVDÊRÎKIRÎ |
| Organisations with AI security policies | percent of surveyed organisations | per survey | Industry surveys | REPORTED |
Where the evidence comes from.
Named public datasets and institutional records, each with its licence class. Sources by agreement are used only under their terms and never republished.
| Çavkanî | What it gives | Licence class |
|---|---|---|
| MITRE ATLAS | Adversarial tactics and techniques against AI pergalan, with case studies | Public, licence to check |
| NIST adversarial machine learning taxonomy | Terminology and taxonomy of attacks and mitigations | Public domain, US government |
| National Vulnerability Database and CVE records | Vulnerabilities in AI software | Public domain, US government |
| ENISA reports on AI cybersecurity | Threat landscape and good practice for securing AI | Public, ENISA terms |
| Joint guidance from national cyber agencies on secure AI system development | Secure design, development, deployment and operation | Public, terms per agency |
Who decides, and what the evidence serves.
Zîrekiya çêkirî û Pergal prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.
| Kî biryarê dide | The question | Evidence this page serves |
|---|---|---|
| Chief information security officers | How to secure AI systems the organisation builds or buys | Threat models; supply chain checklists |
| National cybersecurity agencies | What guidance to issue on AI security | Incident and vulnerability evidence |
| Pêşdebir | Which defences to build into models and applications | Robustness testing; attack taxonomies |
Outputs this topic produces
- Threat models for AI deployments
- AI supply chain security checklists
- Robustness testing protocols
- Evidence notes on AI-enabled attack trends
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?
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.
Security engineering for AI.
- 01
Red-teaming
Structured attempts to break a system, combining ewlehiya sîber û kriptografî and artificial intelligence and machine learning expertise. Red-teaming finds problems but cannot prove their absence.
- 02
Threat modelling
Mapping assets, adversaries and attack paths across data, training, deployment and supply chain.
- 03
Robustness testing
Measuring performance under adversarial perturbation. Robustness to known attacks does not imply robustness to new ones.
- 04
Supply-chain integrity
Provenance of datasets, models and dependencies, with signing and verification. Provenance tooling is still maturing.
How it is studied, and what the methods cannot say.
- 01Ewlehiya sîber û kriptografîThreat modelling AI applications · Model supply chain integrity · Injection defence testingApplied here
- 02Endezyariya nirxandin û teminata zîrekiya çêkirîAssurance cases for AI systems · Structured red teaming · Post-deployment monitoringApplied here
- 03Zîrekiya çêkirî û fêrbûna makîneyêDistribution shift analysis · Fine-tuning for a specific use · Interpretability methodsApplied here
- 04Komputerkirina bi performansa bilind, ewr û kenarCompute access for public research · Energy measurement of workloadsApplied here
Where this page’s references lead.
Sazî û belgeyên ku ev rûpel li hember wan tê xwendin. Rewş û çap diguherin; her girêdan diçe ba saziya derxistinê.
Pirs û bersiv.
What is data poisoning?
What is MITRE ATLAS?
Does AI make cyberattacks easier?
Does the platform publish attack techniques?
How do I report a vulnerability?
Is open release of model weights a security risk?
Can AI defend against AI-enabled attacks?
Ji vê rûpelê delîl bidin.
rêzeya Pergalên Stratejîk 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.
- E-nameDergeh GW-GCRIJi vê rûpelê bişîninDelîl, rastkirin, doz, rêbaz, nirxandin, wergerandin an têketina profîlê. Bi nîşana vê rûpelê digihîje, ji ber vê yekê edîtorê xwediyê wê wê bistîne.
- ZenodoDepoya vekirîWê razînin û ji civakê re bişîninTomara xwe li Zenodo bi ORCID iD ya xwe biweşînin, paşê wê li wir ji civaka Reports re bişînin. Kurator wê vedikolin; DOI ya we dimîne.
- rêzeya Pergalên StratejîkGCRIHemû rêyên beşdariyê bibîneCureyên beşdariyê, her yek çawa tê nirxandin, tu çi navlêkirinê distînî, lîsans û tiştê ku qet nayê qebûlkirin.
Tu carî daneyên şexsî, hûrgiliyên binesaza hesas an tiştekî ku mafê we yê parvekirinê tune ne neşînin. Beşdarî berî bikaranînê tê nirxandin; şandina wê nivîskarî an mafên edîtorî nade û sponsorî tu carî encamekê nakire.
Rêbazek, danehevek an pirsek bîne.
Agahî û pirs îro vekirî ne. Pirsek referansekê distîne û gava piştî wê dide nasîn; serlêdan, drav, veqetandina hesabkirinê û tomarkirin tenê dema ku tîm, mercên wê û kapasîteya vekolînê hebin vedibin.
Belgeyên hiqûqî.
Nexşe, dane û jimarên vê malperê ji bo çarçoveyê û agahiyên giştî têne nîşandan. Ew ne şîret, ne pêşbînî û ne hişyarî ne; sînorên agahiyê di Daxuyaniyên Berpirsiyariyê û Daxuyaniyên Daneyê de hatine diyarkirin.