AI glossary / Safety and trust
Adversarial attack
Feeding an AI a carefully crafted input designed to fool it, such as a sticker that makes a self-driving car misread a road sign.
Think of it as: An optical illusion, but for machines.
More words in Safety and trust
- AI companionA chatbot designed to act as a friend or partner. Popular, and also a concern, because people can become emotionally dependent on it.
- AI detectorA tool that claims to spot AI-written text or AI-made images. They are unreliable and often wrong, so treat results with caution.
- AI ethicsThe study of how to build and use AI in ways that are fair, honest and respectful of people.
- AI governanceThe rules, checks and sign-offs an organisation uses to make sure its AI is used safely and legally.
- AI safetyResearch and engineering aimed at making sure AI systems don't cause harm, by accident or by misuse.