Skip to content
Edition NigeriaGlobal
Country

You are in the Nigeria edition. Type your country to switch.

Set up your profile

AI safety and security at work · Lesson 1 of 9

The AI threat landscape at work

AI assistants, connectors and agents add new entry points to every organisation. This lesson sorts AI threats into threats to people, data and systems, and shows how a four-question threat model and published frameworks help teams defend proportionately.

Intermediate11 min read5 steps

This lesson is complete in writing. A video for it is on its way.

What you will learn

  • Explain why assistants, connectors and agents widen an organisation's attack surface.
  • Sort AI threats into threats to people, data and systems, with a workplace example of each.
  • Run a simple threat model on an AI tool using four questions.
  • Describe, in general terms, the published frameworks security teams use for AI risk.

Key terms in this lesson

Two-factor authentication
A sign-in that needs two different things, such as a password and a code or approval from your phone, so a stolen password alone is not enough. Often shortened to 2FA.
Large language model
An AI model trained on huge amounts of text to understand and generate language.
Social engineering
Manipulating people, rather than computers, into giving away details, codes or money, usually through trust, fear or urgency.
Attack surface
All the points where an attacker could try to get into or misuse a system, such as inputs, connected tools, suppliers and outputs.
Threat model
A structured description of what could go wrong with a system, who might cause it and how the organisation will defend against it, reviewed as the system changes.
EU AI Act
The European Union's law on artificial intelligence, which sorts AI uses into risk tiers and places the heaviest duties on uses it treats as high risk, such as credit scoring of individuals.
Personal data
Any information that identifies you or could be linked to you, such as your name, account numbers, address, ID number or voice.

Step 1 of 5

What changes when AI arrives at work

Opening this step…

Step 2 of 5

Threats to people, data and systems

This step opens when you finish the one above.

Step 3 of 5

Mapping the attack surface

This step opens when you finish the one above.

Step 4 of 5

Threat modelling in four questions

This step opens when you finish the one above.

Step 5 of 5

Published frameworks, and your part

This step opens when you finish the one above.

Key takeaways

The key takeaways open when you finish every step.

Lesson quiz

5 questions. You need 85% to pass.

The quiz opens when you finish every step.

Stockertim Learn is education. It explains how investing works and never recommends buying or selling anything.

Up next

English