Skip to content

GCRI · زیرەکی دەستکرد و سیستەمە خۆسەرەکان

ئاسایشی سایبەریی زیرەکی دەستکرد

AI and cybersecurity meet in three ways: AI سیستەمە 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.

01تۆمارکردن

AI cyber security on the record.

02The question

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.

میکانیزم

Models are attack surfaces

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

میکانیزم

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.

میکانیزم

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.

میکانیزم

AI assists defence

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

03ئەنجامدەر

زنجیرەی کاریگەرییەک بە تۆڕە پشتبەستوو بە یەکترەکاندا.

A شوێنپێی مەترسیدەر موڵکی هاوشوێن لە هەموو چینەکاندا لەناو دەبات؛ پاشان پارچەپارچەبوون، پشتبەستنی نێوان چینەکان و بارزۆری ڕزگاربووان شکستەکە بڵاو دەکەنەوە. بینینی 3D چینەکان بە قووڵایی جیا دەکاتەوە. مۆدێلی فێرکاری بە بەهای نموونەیی ڕاگەیەندراو، نەک پێشبینی.

کۆنترۆڵەکان

موڵک بۆ هەر چینێک
18
شوێنپێی مەترسیدەر
8% ی ناوچەکە
موڵکی پشتبەستوو بە چینێکی دیکە
60%
توانای یەدەگ (ڕێژەی قبووڵکردن)
30%

خوێندنەوەکان

موڵکی کەوتووە بەر مەترسیدەر
7%
موڵکی هێشتا کارکەر
50%
زیادبوونی زیانی سەرەتایی
6.8 times
هەنگاوەکانی یەکلاکردنەوە
3
ژمارە، ڕێگا و سەرچاوەکان
هەنگاوناوەندی داتای کارکەر (%)تۆڕی کارکەر (%)هێزی کارکەر (%)
08394100
1727894
2616750
3616722

میتۆدەکان

  1. تۆڕە پشتبەستوو بە یەکترەکان Buldyrev و ئەوانی دیکە (2010)، Catastrophic cascade of failures in interdependent networks، Nature 464
  2. زنجیرەی بارزۆری Motter و Lai (2002)، Physical Review E 66
  3. بارگرانی ناوەندێتی نێوانی Brandes (2001)، Journal of Mathematical Sociology 25
  4. تۆڕە فرە چینەکان Kivela و ئەوانی دیکە (2014)، Journal of Complex Networks 2
  5. پشتبەستنی ژێرخانەکان بە یەکتر Rinaldi، Peerenboom و Kelly (2001)، IEEE Control Systems 21(6)
  6. پەنجەی نادڵنیایی (مۆنتی کارلۆی پارامیتەر) Spiegelhalter, Pearson و Short (2011)، Visualising uncertainty about the future، Science 333
  7. هەستیاریی یەک-یەک (تۆرناد) Saltelli و ئەوانی دیکە (2008)، Global Sensitivity Analysis: The Primer، Wiley

داتا

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:

  • ڕێگا سەرەکییەکان Natural Earth
  • هێڵی شەمەندەفەر Natural Earth
  • بەندەرە دەریاییەکان Natural Earth
  • فڕۆکەخانەکان Natural Earth
  • بەرینی شارەکان Natural Earth
  • ڕووناکی شەو ئەمشەو، پچڕانەکان (VIIRS Day/Night Band) NASA/NOAA VIIRS (Suomi NPP) · register nasa.gibs.context-live-layers
  • ڕووداوە سروشتییەکان (NASA EONET) NASA EONET · register nasa.eonet.events
زنجیرەی کاریگەرییەک بە تۆڕە پشتبەستوو بە یەکترەکاندا. مۆدێلی فێرکاریی نموونەیی: لەسەر ئەو بەهایانە کار دەکات کە کۆنترۆڵەکان دایاندەنێن، نەک داتای پێوراو. ڕێگاکان: تۆڕە پشتبەستوو بە یەکترەکان (Buldyrev و ئەوانی دیکە (2010)، Catastrophic cascade of failures in interdependent networks، Nature 464)؛ زنجیرەی بارزۆری (Motter و Lai (2002)، Physical Review E 66)؛ بارگرانی ناوەندێتی نێوانی (Brandes (2001)، Journal of Mathematical Sociology 25).
04لە ناو بوارەکان

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

05ڕێگا و بەڵگە

How AI cyber security is modelled, measured and tested.

مۆدێلەکە، گریمانەکانی، داتاکانی و نادڵنیاییەکەی، بەو شێوەیەی زانا یان ئەندازیارێک دەیپشکنێت. پێکهاتەکان ڕێگا بڵاوکراوەکان دەگرنەبەر. بەهاکانی کێشراو نموونەییە، نەک دۆزینەوە.

مۆدێلی سیستەم

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

++−+زیرەکی دەستکردداتاکۆمەڵگە خۆجێییەکانئابووریR بەهێزکەرB هاوسەنگ
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.
پرەنسیپە ڕێنماییەکانی FAIR · GO FAIR و FORCE11W3C PROV · World Wide Web Consortiumڕێنمایی بۆ مامەڵەی یەکسان لەگەڵ نادڵنیاییەکان · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
06نیشاندەرەکان

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.

IndicatorUnitCadenceSource typeناونیشان
Vulnerabilities reported in AI frameworks and librariescount of CVE entriesmonthlyVulnerability databasesREPORTED
Adversarial robustnessaccuracy under a stated attackper evaluationRobustness testingچاودێریکراو
Models with signed provenancepercent of deployed modelsper inventoryModel registriesDECLARED
AI-related security incidentscount by techniqueannualIncident reportsREPORTED
Time to detect AI system compromisehoursper incidentIncident response recordsچاودێریکراو
Organisations with AI security policiespercent of surveyed organisationsper surveyIndustry surveysREPORTED
07سەرچاوەکان

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.

سەرچاوەWhat it givesLicence class
MITRE ATLASAdversarial tactics and techniques against AI سیستەمە, 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
08بڕیارەکان

Who decides, and what the evidence serves.

زیرەکی دەستکرد و سیستەم prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

کێ بڕیار دەداتThe questionEvidence this page serves
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
گەشەپێدەرانWhich defences to build into models and applicationsRobustness 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
09Core questions

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?
10Mechanisms

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.

11Methods and data

Security engineering for AI.

  1. 01

    Red-teaming

    Structured attempts to break a system, combining ئاسایشی سایبەری و نهێنینووسی 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.

ئەو لەش و بەڵگەنامانەی ئەم لاپەڕەیەیان لەگەڵ دەخوێنرێتەوە. دۆخ و وەشانەکان دەگۆڕێن؛ هەر بەستەرێک دەچێتە لای لەشی دەرکەر.

14پرسیارەکان

پرسیار و وەڵام.

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?
نووسین بۆ فۆرمی ڕاپۆرتی ئاسایش. The acknowledgement gives a reference and names the next step.
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.
Reportsبەشداربە

لەم لاپەڕەیەوە بەڵگە پێشکەش بکە.

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.

GCRIزیرەکی دەستکرد و سیستەمە خۆسەرەکانتەکنەلۆجیای ئێکسپۆنێنشیاڵبەڵگەی Labs
زیرەکی دەستکرد و سیستەمە خۆسەرەکان

ڕێگایەک، کۆمەڵە داتایەک یان پرسیارێک بهێنە.

زانیاری و پرسیار ئەمڕۆ کراوەن. پرسیارێک ژمارەی ئاماژەی پێدەدرێت و هەنگاوی دواتر دیاری دەکات؛ داواکاری، پارەدان، تەرخانکردنی کۆمپیوتەر و تۆمارکردن تەنیا کاتێک دەکرێنەوە کە تیم، مەرج و توانای پێداچوونەوەیان هەبێت.