🛡️ AI Security

Access control sets rules about which people, systems or AI tools can view, use or change specific data, functions and resources.

AI security protects AI systems, their inputs, outputs and connected tools from manipulation, misuse, theft and unauthorised access.

Authentication verifies a claimed identity; authorisation checks what that requester is allowed to do.

The practice of storing and using passwords, tokens and keys safely so people and software can reach services without exposing those credentials.

Use of AI tools outside approved organisational processes, especially where data, security, legal or oversight rules are bypassed.

An adversarial attack is a deliberate attempt to exploit an AI system so it fails or produces an attacker-chosen result.

Unauthorised copying of information out of a system, application or connected tool to a place an attacker or unapproved user can access.

An attack that quietly corrupts training data by adding, changing or removing examples, causing wrong patterns or a hidden trigger in the model.

A jailbreak is a prompt or sequence of prompts designed to make an AI assistant ignore or work around its safety and behaviour limits.

A text-based attack that tries to make an AI assistant follow hidden or malicious instructions instead of the rules and task it was meant to follow.

Sandboxing runs a model, tool or file inside a restricted environment so harmful actions cannot easily reach the wider system.

A small, carefully chosen change to an input can push a model towards a wrong output while looking almost unchanged to a person.

A malicious instruction in external content tries to make a model follow it instead of the user’s or system’s intended task.

Model extraction tries to copy model behaviour, while model inversion uses model information to reconstruct training-data features or examples.