Skip to content

GCRI · Zîrekiya çêkirî û pergalên xweser

Cybersecurity for AI systems

Cybersecurity and cryptography protect AI pergalan and the data they use. In this field the focus is threats specific to AI, such as prompt injection, poisoning and model theft, alongside conventional security of the software and infrastructure around models.

01Qeyd

Cybersecurity for AI systems on the record.

Method recordSTEM method
  1. RêbazEwlehiya sîber û kriptografî
  2. Applied inZîrekiya çêkirî û Pergal
  3. Canonical pageSTEM Commons
02Application

What cybersecurity and cryptography does here.

Cybersecurity and cryptography protect information pergalan and data from unauthorised access, disruption and manipulation. They address threats that can spread rapidly across interconnected digital and physical systems. In artificial intelligence and data and compute, cybersecurity analysis identifies how a single compromise can propagate across sectors that share software, vendors or networks. It informs resilience requirements and cyber insurance. The canonical description is on STEM Commons.

Threat modelling AI applications

Data flows, trust boundaries and tools of an AI application are mapped to identify where untrusted inputs could manipulate the model or where data could leak.

Model supply chain integrity

Provenance of datasets and model weights is recorded and verified with signatures and hashes before use.

Injection defence testing

Applications are tested with suites of injection attempts, and the success rate is tracked as defences change.

03Çavdêrî bike

Security assessment.

The screen a team would use to follow this method: its measures, states and decisions. Names are examples and values are illustrative.

Security assessment

AI and autonomous systems · Cybersecurity for AI systems · Run R-5953

Two high findingsGCRI · Zîrekiya çêkirî û pergalên xweser

Encam

Weak key rotationIdentity serviceBilindPR.AAVekirî
Unpatched gatewayEdgeBilindPR.PSFixing
Logging gapAPI ya dayînêNavînDE.CMVekirî
Stale accountsRêberKêmPR.AAClosed

Method card

Rêbaz
Ewlehiya sîber û kriptografî
Framework
Fonksiyonên CSF 2.0
Çarçove
54 assets
Nîşan
MODELKIRÎ

Control coverage by function

Security assessment: the screen’s structure, terms and states for AI and autonomous systems.Nav û nirxên nimûneyî; sêwiran e, ne qeyd an pergaleke zindî ye.
04Dane

What the method consumes.

Datasets and records used by cybersecurity and cryptography on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.

DaneRolNîşan
MITRE ATLAS techniquesThreat catalogueREPORTED
Vulnerability databasesKnown flawsREPORTED
Security test resultsDefence performanceÇAVDÊRÎKIRÎ
05Simulator

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
2%
Mal û milkên ku hê dixebitin
72%
Mezinbûna zerara destpêkê
15.0 times
Gavên çareserkirinê
3
Jimar, rêbaz û çavkanî
GavNavendên daneyê yên ku dixebitin (%)Tor yên ku dixebitin (%)Hêz dixebite (%)
094100100
18967100
27267100
3726778

Rêbaz

  1. Torên girêdayî Buldyrev û yên din (2010), Catastrophic cascade of failures in interdependent networks, Nature 464
  2. Zincîra barkêşiya zêde Motter and Lai (2002), Physical Review E 66
  3. Barê navbeynkariyê Brandes (2001), Journal of Mathematical Sociology 25
  4. Torên pirqat Kivela and others (2014), Journal of Complex Networks 2
  5. Girêdayîbûnên binesazê Rinaldi, Peerenboom and Kelly (2001), IEEE Control Systems 21(6)
  6. Pankeya nediyarîyê (Monte Carlo ya parametreyan) Spiegelhalter, Pearson and Short (2011), Visualising uncertainty about the future, Science 333
  7. 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
Zincîra bandorê di torên girêdayî de. Modela fêrkirinê ya nimûneyî: ew li ser nirxên ku kontrol destnîşan dikin dimeşe, ne li ser daneyên pîvandî. Rêbaz: Torên girêdayî (Buldyrev and others (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).
06Erêkirin

How results are checked.

Controls are tested through red-team exercises, audits and formal analysis of cryptographic schemes. Incident data are used to check whether defences performed as intended.

Kontrol bikinHow it is done
Threat model reviewThreat models are reviewed when the application or its tools change
Provenance verificationModel artefacts are checked against signed records
Regression testingSecurity tests are rerun after each update

Adversaries adapt, so historical data may not reflect future attacks. Software supply chains and legacy systems introduce weaknesses that are hard to inventory.

07Rêbaz û delîl

How Cybersecurity for AI systems 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.

Model, hevkêşe û texmîn

The model structure used for Cybersecurity for AI systems, the assumptions it makes and how each is tested.

Xetera hêmana iRi = f(Hi, Ei, Vi, Ci)metirsî, rûbirûbûn, lawazî û kapasîteya serederiyê
Windahiya salane ya hêvîkirîEAL = ∑k pk · Lkli ser bûyerên k bi îhtîmala salane pk
Pergalên girêdayîxt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error
TexmînÇima tê çêkirinÇawa tê ceribandin
Metirsî û rûbirûbûn di nav bûyerekê de serbixwe neEntegrala windahiyê ji hesabkirinê re maqûl dihêleBi lihevhatineke copula li ser tomarên hevbeş re bidin ber hev
Girêdan li nêzî xala xebatê xêzik inDihêle şok di A de belav bibinJi derveyî rêza xêzik tevlihev bike û bide ber hev
Xêzên lawaziyê di navbera cihan de têne veguhastinXêzikên herêmî kêm tên dîtinLi hember windahiyên çavdêrîkirî erê bike li cihê ku hene
Têketin
danehevên bi guhertoyan û çavkaniyê
Derketin
belavkirin, tu carî jimarên tenê
Kod
bi qerta modelê û ceribandinan re hat weşandin
Zêdebûn
heman dane, kod, jîngeh û tov
Formulasyonên standard ên xetereyê û qada rewşê; texmînên navborî ji bo rêbazê tîpîk in, ji bo nirxandinê hatine diyarkirin, ne encam in.
Prensîbên rêber ên FAIR · GO FAIR û FORCE11W3C PROV · World Wide Web ConsortiumRêwerzên ji bo birêvebirina hevgirtî ya nediyarîyan · IPCCCEOS Analysis Ready Data · Committee on Earth Observation Satellites
08Connections

Topics that rely on this method.

09Stewardship

Who maintains the method.

Ewlehiya sîber û berxwedana dîjîtal stewards cybersecurity and cryptography for the Consortium and reviews how it is applied across platforms.

11Pirs

Pirs û bersiv.

What are the limits of cybersecurity and cryptography in this field?
Adversaries adapt, so historical data may not reflect future attacks. Software supply chains and legacy systems introduce weaknesses that are hard to inventory.
How are results checked?
Controls are tested through red-team exercises, audits and formal analysis of cryptographic schemes. Incident data are used to check whether defences performed as intended.
Are the values on this page real?
The data names, roles and checks are real descriptions of practice. The canvas shows a design of the method’s use, not a run; no result is reported here.
Where else is this method applied?
Çavdêrxaneya canonical method page lists every platform that applies it.
rêzeya Pergalên StratejîkTevkarî bike

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.

GCRIZîrekiya çêkirî û pergalên xweserTeknolojiya eksponensiyelDelîlên Labs
Zîrekiya çêkirî û pergalên xweser

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.