Skip to content

GCRI · 人工智能与自主系统

面向人工智能系统的网络安全

Cybersecurity and cryptography protect AI 系统 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.

提出咨询 Back to STEM foundation of Artificial Intelligence and Autonomous Systems
01登记

Cybersecurity for AI systems on the record.

方法记录STEM 方法
  1. 方法网络安全与密码学
  3. 应用于人工智能与自主 系统
  4. 数据3 inputs
  6. 规范页面STEM 公共资源
02申请

What cybersecurity and cryptography does here.

Cybersecurity and cryptography protect information 系统 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.

03监测

Security assessment.

团队遵循该方法时会使用的界面：其指标、状态与决策。名称为示例，数值仅作示意。

Security assessment

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

Two high findingsGCRI · 人工智能与自主系统

发现

Weak key rotationIdentity service高PR.AA打开
Unpatched gatewayEdge高PR.PSFixing
Logging gap支付 API中DE.CM打开
Stale accounts名录低PR.AA已关闭

方法卡

方法
网络安全与密码学
框架
CSF 2.0 功能
范围
54 assets
标签
模型生成

Control coverage by function

Security assessment: the screen’s structure, terms and states for AI and autonomous systems.示例名称和示意数值；是设计方案，并非记录或实时系统。
04数据

该方法使用的输入。

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 来源登记册.

数据角色标签
MITRE ATLAS techniquesThreat catalogue已报告
Vulnerability databasesKnown flaws已报告
Security test resultsDefence performance观测
05模拟器

在相互依存的网络中的一次级联。

A 危害足迹 会摧毁每一层中位于同处的资产；随后，碎片化、层间依赖和幸存资产的过载使失效扩散开来。3D 视图按深度分开各层。这是带有说明性取值的教学模型，不是预测。

控制措施

每个图层的资产
18
危害足迹
占面积的 8%
依赖其他图层的资产
60%
备用容量（容差）
30%

读数

受危害冲击的资产
2%
仍在运行的资产
72%
初始损害的放大
15.0 times
结算步数
3
数字、方法与来源
步骤运行中的数据中心（%）运行中的网络（%）电力运行（%）
094100100
18967100
27267100
3726778

方法

  1. 相互依存网络 Buldyrev 等（2010），Catastrophic cascade of failures in interdependent networks，Nature 464
  2. 过载级联 Motter and Lai (2002), Physical Review E 66
  3. 介数负载 Brandes (2001), Journal of Mathematical Sociology 25
  4. 多层网络 Kivela and others (2014), Journal of Complex Networks 2
  5. 基础设施相互依赖 Rinaldi, Peerenboom and Kelly (2001), IEEE Control Systems 21(6)
  6. 不确定性扇形图（参数蒙特卡罗） Spiegelhalter, Pearson and Short (2011), Visualising uncertainty about the future, Science 333
  7. 单因素敏感性（龙卷风图） Saltelli and others (2008), Global Sensitivity Analysis: The Primer, Wiley

数据

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:

  • 主要道路 Natural Earth
  • 铁路 Natural Earth
  • 海港 Natural Earth
  • 机场 Natural Earth
  • 城市范围 Natural Earth
  • 今晚的夜间灯光、停电（VIIRS 昼夜波段） NASA/NOAA VIIRS（Suomi NPP）· 登记 nasa.gibs.context-live-layers
  • 自然事件（NASA EONET） NASA EONET · 登记 nasa.eonet.events
级联在相互依存的网络中传播。示意性教学模型：它依据控件设定的数值运行，而非实测数据。方法：Interdependent networks (Buldyrev and others (2010), Catastrophic cascade of failures in interdependent networks, Nature 464)；Overload cascades (Motter and Lai (2002), Physical Review E 66)；Betweenness load (Brandes (2001), Journal of Mathematical Sociology 25)。

贯穿六大支柱，由 Nexus Consortium 牵头

06验证

结果如何核查。

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.

核查如何开展
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.

07方法与证据

How Cybersecurity for AI systems is modelled, measured and tested.

模型、其假设、数据和不确定性，以科学家或工程师会核查的形式呈现。结构遵循已发表的方法。所取数值仅为示意，不是研究发现。

模型、方程与假设

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

要素 i 的风险Ri = f(Hi, Ei, Vi, Ci)危害、风险暴露、脆弱性和应对能力
预期年度损失EAL = ∑k pk · Lk对年概率为 pk
耦合系统xt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error
假设为何制作如何检验
在一次事件中，危害与暴露相互独立使损失积分保持可计算与基于联合记录拟合的 copula 进行比较
耦合在工作点附近是线性的让冲击通过 A 传播在线性范围之外施加扰动并比较
脆弱性曲线可以在不同地点之间迁移使用很少有本地曲线可用在有观测损失的地方据此进行验证
输入
带溯源信息的版本化数据集
成果
分布，绝不是单一数字
代码
连同模型卡和测试一起发布
复现
相同的数据、代码、环境和随机种子
标准的风险与状态空间表述；所列假设是该方法的典型假设，供审查之用，并非结果。
FAIR 指导原则 · GO FAIR 和 FORCE11W3C PROV · 万维网联盟关于一致处理不确定性的指南 · IPCCCEOS 分析就绪数据 · 地球观测卫星委员会
08关联

依赖该方法的主题。

09管理责任

由谁维护该方法。

网络安全与数字韧性 stewards cybersecurity and cryptography for the Consortium and reviews how it is applied across platforms.

Canonical page: Cybersecurity and cryptography

10已关联

本页在整个联合体中通向何处。

11问题

问题与解答。

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.
结果如何核查？
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.
本页面上的数值是真实的吗？
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.
该方法还应用于何处？
维持社会运转的 规范方法页面 列出应用该方法的每个平台。
报告贡献

从本页贡献证据。

报告 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.

GCRI人工智能与自主系统指数级技术Labs 证据

切勿发送个人数据、敏感基础设施细节或您无权分享的任何内容。贡献在使用前会经过审查；发送贡献不赋予署名权或编辑权，赞助也绝不能换取研究结论。

人工智能与自主系统

带来一种方法、一个数据集或一个问题。

信息和咨询现已开放。每项咨询都会获得一个编号，并告知下一步；申请、付款、算力分配和注册只有在相应团队、条款和审查能力就绪时才会开放。

提出一种方法 查看全部联系途径
法律

本网站上的地图、数据和图表仅作为背景和一般信息展示。它们不是建议、预测或预警；信息的局限见免责声明和数据说明。