GCRI · Kecerdasan Buatan dan Sistem Otonom
Keamanan siber AI
AI and cybersecurity meet in three ways: AI sistem 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.
Efek berantai melalui jaringan yang saling bergantung.
A Jejak bahaya melumpuhkan aset yang berada di lokasi sama pada setiap lapisan; fragmentasi, ketergantungan antarlapisan, dan kelebihan beban pada yang selamat kemudian menyebarkan kegagalan. Tampilan 3D memisahkan lapisan menurut kedalaman. Model pengajaran dengan nilai ilustratif yang dinyatakan, bukan prediksi.
Kendali
- Aset per lapisan
- 18
- Jejak bahaya
- 8% dari luas wilayah
- Aset yang bergantung pada lapisan lain
- 60%
- Kapasitas cadangan (toleransi)
- 30%
Pembacaan
- Aset yang terdampak bahaya
- 7%
- Aset yang masih berfungsi
- 50%
- Penguatan kerusakan awal
- 6.8 times
- Langkah menuju stabil
- 3
Angka, metode, dan sumber
| Langkah | Pusat data berfungsi (%) | Jaringan berfungsi (%) | Daya berfungsi (%) |
|---|---|---|---|
| 0 | 83 | 94 | 100 |
| 1 | 72 | 78 | 94 |
| 2 | 61 | 67 | 50 |
| 3 | 61 | 67 | 22 |
Metode
- Jaringan yang saling bergantung Buldyrev dan lainnya (2010), Catastrophic cascade of failures in interdependent networks, Nature 464
- Rambatan kelebihan beban Motter and Lai (2002), Physical Review E 66
- Beban keantaraan Brandes (2001), Journal of Mathematical Sociology 25
- Jaringan multilapis Kivela and others (2014), Journal of Complex Networks 2
- Saling ketergantungan infrastruktur Rinaldi, Peerenboom and Kelly (2001), IEEE Control Systems 21(6)
- Kipas ketidakpastian (Monte Carlo parameter) Spiegelhalter, Pearson and Short (2011), Visualising uncertainty about the future, Science 333
- Sensitivitas satu per satu (tornado) Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley
Data
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:
- Jalan utama Natural Earth
- Jalur kereta api Natural Earth
- Pelabuhan laut Natural Earth
- Bandar udara Natural Earth
- Luasan perkotaan Natural Earth
- Cahaya malam hari ini, pemadaman (VIIRS Day/Night Band) NASA/NOAA VIIRS (Suomi NPP) · register nasa.gibs.context-live-layers
- Peristiwa alam (NASA EONET) NASA EONET · register nasa.eonet.events
Di seluruh enam pilar, dipimpin oleh Nexus Consortium
- Eksperimen Laboratorium
- Tertanam di Kecerdasan Buatan dan Sistem Otonom di Foundry
- Diuji pada Kecerdasan Buatan dan Sistem Otonom di Universe
- Dikodifikasi dalam Digital, Siber, dan AI di Standards
- Diterbitkan di Kecerdasan Buatan dan Sistem Otonom di Reports
- Diajarkan di Fakultas Teknologi dan Sistem Digital di Academy
AI changes cyber risk in every domain’s control systems.
Findings are designed for the seri Teknologi Eksponensial. 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, asumsi, data, dan ketidakpastiannya, dalam bentuk yang akan diperiksa ilmuwan atau insinyur. Strukturnya mengikuti metode yang dipublikasikan. Nilai yang digambar bersifat ilustratif, bukan temuan.
Model sistem
The couplings between the systems in AI cyber security: signs of influence, a reinforcing and a balancing loop, and cross-links where stress jumps.
Apa yang diukur, dan seberapa baik.
Setiap indikator membawa satuan, frekuensi, jenis sumber di baliknya, dan label bukti yang akan dibawa suatu nilai. Tidak ada nilai yang ditampilkan: sebuah program menyediakannya berdasarkan wewenangnya sendiri.
| Indikator | Unit | Kadensi | Jenis sumber | Label |
|---|---|---|---|---|
| Vulnerabilities reported in AI frameworks and libraries | count of CVE entries | setiap bulan | Vulnerability databases | DILAPORKAN |
| Adversarial robustness | accuracy under a stated attack | per evaluation | Robustness testing | TERAMATI |
| Models with signed provenance | percent of deployed models | per inventory | Model registries | DINYATAKAN |
| AI-related security incidents | count by technique | tahunan | Incident reports | DILAPORKAN |
| Time to detect AI system compromise | hours | per incident | Incident response records | TERAMATI |
| Organisations with AI security policies | percent of surveyed organisations | per survey | Industry surveys | DILAPORKAN |
Asal bukti.
Set data publik bernama dan catatan kelembagaan, masing-masing dengan kelas lisensinya. Sumber berdasarkan perjanjian hanya digunakan sesuai ketentuannya dan tidak pernah diterbitkan ulang.
| Sumber | Apa yang diberikannya | Kelas lisensi |
|---|---|---|
| MITRE ATLAS | Adversarial tactics and techniques against AI sistem, 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 |
Siapa yang memutuskan, dan apa yang dilayani bukti.
Studio Kecerdasan Buatan dan Sistem prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.
| Siapa yang memutuskan | Pertanyaannya | Bukti yang dilayani halaman ini |
|---|---|---|
| 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 |
| Pengembang | Which defences to build into models and applications | Robustness testing; attack taxonomies |
Keluaran yang dihasilkan topik ini
- 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 keamanan siber dan kriptografi and artificial intelligence and machine learning expertise. Red-teaming finds problems but cannot prove their absence.
- 02
Pemodelan ancaman
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.
Cara hal ini dikaji, dan apa yang tidak dapat dinyatakan metodenya.
- 01Keamanan siber dan kriptografiPemodelan ancaman aplikasi AI · Integritas rantai pasok model · Pengujian pertahanan terhadap injeksiDiterapkan di sini
- 02Evaluasi AI dan rekayasa penjaminanKasus penjaminan untuk sistem AI · Red teaming terstruktur · Pemantauan pascapenerapanDiterapkan di sini
- 03Kecerdasan buatan dan pembelajaran mesinAnalisis pergeseran distribusi · Fine-tuning untuk penggunaan tertentu · Metode interpretabilitasDiterapkan di sini
- 04Komputasi berkinerja tinggi, cloud, dan edgeAkses komputasi untuk riset publik · Pengukuran energi beban kerjaDiterapkan di sini
Where this page’s references lead.
Badan dan dokumen yang menjadi acuan halaman ini. Status dan edisi berubah; setiap tautan menuju badan penerbitnya.
Tanya jawab.
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?
Kontribusikan bukti dari halaman ini.
Laporan 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.
- SurelGerbang GW-GCRIKirim dari halaman iniBukti, koreksi, kasus, metode, tinjauan, terjemahan, atau masukan profil. Kiriman tiba dengan label halaman ini, sehingga editor pemiliknya menerimanya.
- ZenodoDeposit terbukaDeposit dan ajukan ke komunitasTerbitkan catatan Anda sendiri di Zenodo dengan ORCID iD Anda, lalu ajukan ke komunitas Reports di sana. Kurator meninjaunya; DOI tetap milik Anda.
- LaporanGCRILihat semua cara berkontribusiJenis kontribusi, cara masing-masing ditinjau, kredit yang Anda terima, lisensinya, dan apa yang tidak pernah diterima.
Jangan pernah mengirim data pribadi, rincian infrastruktur sensitif, atau apa pun yang tidak berhak Anda bagikan. Kontribusi ditinjau sebelum digunakan. Mengirimkannya tidak memberikan hak kepenulisan atau editorial, dan sponsor tidak pernah membeli sebuah temuan.
Bawa metode, dataset, atau pertanyaan.
Informasi dan pertanyaan sudah terbuka hari ini. Sebuah pertanyaan menerima nomor referensi dan menyebutkan langkah berikutnya; lamaran, pembayaran, alokasi komputasi, dan pendaftaran hanya dibuka ketika tim, ketentuan, dan kapasitas tinjauannya tersedia.
Dokumen hukum.
Peta, data, dan gambar di situs ini ditampilkan untuk konteks dan informasi umum. Semua itu bukan nasihat, prakiraan, atau peringatan; batasan informasinya dijelaskan dalam Penafian dan Pemberitahuan Data.