Skip to content

GCRI · 인공지능과 자율 시스템

AI 사이버보안

AI and cybersecurity meet in three ways: AI 시스템 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.

01등록

AI cyber security on the record.

02질문

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.

메커니즘

Models are attack surfaces

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

메커니즘

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.

메커니즘

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.

메커니즘

AI assists defence

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

03시뮬레이터

상호 의존하는 네트워크를 통한 연쇄.

A 재해 영향 범위 은 모든 층에서 같은 곳에 있는 자산을 무너뜨리고, 이어서 분절, 층 간 의존과 남은 자산의 과부하가 장애를 퍼뜨립니다. 3D 보기는 층을 깊이로 분리합니다. 예시 값을 밝힌 교육용 모델이며 예측이 아닙니다.

통제 수단

레이어별 자산
18
재해 영향 범위
면적의 8%
다른 레이어에 의존하는 자산
60%
예비 용량(허용치)
30%

판독값

재해의 타격을 받은 자산
7%
여전히 작동하는 자산
50%
초기 피해의 증폭
6.8 times
정착까지의 단계
3
수치, 방법과 출처
단계작동 중인 데이터센터(%)작동 중인 네트워크(%)전력 작동(%)
08394100
1727894
2616750
3616722

방법

  1. 상호의존 네트워크 Buldyrev 외(2010), Catastrophic cascade of failures in interdependent networks, Nature 464
  2. 과부하 캐스케이드 Motter and Lai (2002), Physical Review E 66
  3. 매개 부하 Brandes (2001), Journal of Mathematical Sociology 25
  4. 다층 네트워크 Kivela and others (2014), Journal of Complex Networks 2
  5. 인프라 상호 의존성 Rinaldi, Peerenboom and Kelly (2001), IEEE Control Systems 21(6)
  6. 불확실성 팬(매개변수 몬테카를로) Spiegelhalter, Pearson and Short (2011), Visualising uncertainty about the future, Science 333
  7. 단일 요인 민감도(토네이도) Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley

데이터

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:

  • 주요 도로 Natural Earth
  • 철도 Natural Earth
  • 항구 Natural Earth
  • 공항 Natural Earth
  • 도시 범위 Natural Earth
  • 오늘 밤 야간 조명, 정전(VIIRS 주야간 밴드) NASA/NOAA VIIRS(Suomi NPP) · 등록 nasa.gibs.context-live-layers
  • 자연 사건(NASA EONET) NASA EONET · 등록 nasa.eonet.events
상호 의존적인 네트워크를 통한 연쇄 반응. 예시용 교육 모형으로, 측정 데이터가 아니라 조절 장치로 설정한 값에 따라 작동합니다. 방법: 상호 의존 네트워크(Buldyrev and others (2010), Catastrophic cascade of failures in interdependent networks, Nature 464), 과부하 연쇄(Motter and Lai (2002), Physical Review E 66), 매개 중심성 부하(Brandes (2001), Journal of Mathematical Sociology 25).
04영역 전반

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

05방법과 근거

How AI cyber security is modelled, measured and tested.

모형, 그 가정, 데이터, 불확실성을 과학자나 엔지니어가 확인할 형태로 제시합니다. 구조는 발행된 방법을 따릅니다. 제시된 값은 예시이며 결과가 아닙니다.

시스템 모형

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

++−+인공지능데이터지역사회경제R 강화B 균형
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.
FAIR 지침 원칙 · GO FAIR와 FORCE11W3C PROV · 월드 와이드 웹 컨소시엄불확실성의 일관된 처리에 관한 지침 · IPCCCEOS 분석 준비 데이터(Analysis Ready Data) · 지구관측위성위원회
06지표

측정되는 것과 그 정확도.

각 지표에는 단위, 주기, 그 뒤의 출처 종류, 값에 붙을 근거 표시가 있습니다. 값은 표시하지 않습니다. 값은 프로그램이 자체 권한으로 제공합니다.

지표단위주기출처 유형라벨
Vulnerabilities reported in AI frameworks and librariescount of CVE entries월별Vulnerability databases보고됨
Adversarial robustnessaccuracy under a stated attackper evaluationRobustness testing관측
Models with signed provenancepercent of deployed modelsper inventoryModel registries신고됨
AI-related security incidentscount by technique연간Incident reports보고됨
Time to detect AI system compromisehoursper incidentIncident response records관측
Organisations with AI security policiespercent of surveyed organisationsper surveyIndustry surveys보고됨
07출처

근거의 출처.

이름이 명시된 공개 데이터셋과 기관 기록으로, 각각 라이선스 등급이 있습니다. 협약에 따른 출처는 그 조건에 따라서만 사용하며 결코 재게시하지 않습니다.

출처제공하는 것라이선스 등급
MITRE ATLASAdversarial tactics and techniques against AI 시스템, 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
08결정

누가 결정하며 근거는 무엇에 쓰이는지.

인공지능과 자율 시스템 prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

결정 주체질문이 페이지가 제공하는 근거
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
개발자Which defences to build into models and applicationsRobustness testing; attack taxonomies

이 주제가 생산하는 산출물

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

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?
10메커니즘

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.

11방법과 데이터

Security engineering for AI.

  1. 01

    Red-teaming

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

  2. 02

    위협 모델링

    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.

이 페이지를 읽을 때 기준이 되는 기구와 문서. 상태와 판은 바뀌며, 각 링크는 발행 기구로 연결됩니다.

14질문

질문과 답변.

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?
보낼 곳 보안 보고 양식으로 보내 주십시오. 접수 확인에는 참조 번호와 다음 단계가 안내됩니다.
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.
보고서기여하기

이 페이지에서 증거를 기여하십시오.

보고서 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.

GCRI인공지능과 자율 시스템기하급수 기술Labs 근거
인공지능과 자율 시스템

방법, 데이터세트 또는 질문을 가져오십시오.

정보와 문의는 오늘부터 열려 있습니다. 문의에는 참조 번호가 부여되고 다음 단계가 안내됩니다. 신청, 결제, 컴퓨팅 할당, 등록은 해당 팀, 약관, 심사 역량이 갖추어졌을 때만 열립니다.