AI security glossary
Short, plain definitions of the terms in our briefs and guides. Each one links to the full explainer.
A
- AI pentesting
Using AI agents to probe a website or system for weak spots the way an attacker would, with the owner’s permission.
Read more about AI pentesting →- API credential
A secret key that lets software use a paid service on your account. Whoever holds it can run up charges in your name.
Read more about API credential →
B
- Bad bot
Automated traffic that scrapes content, tries stolen passwords or probes for weaknesses, as opposed to useful bots such as search crawlers.
Read more about Bad bot →
C
- Credential stuffing
Trying username and password pairs leaked from one site against the login pages of other sites, at scale.
Read more about Credential stuffing →- CVE
Common Vulnerabilities and Exposures: a public ID given to a known security flaw, so vendors and admins can refer to the same bug.
Read more about CVE →
D
- Distillation attack
Querying an AI model at scale and using its answers to train a cheaper copy of it, often with someone else’s API credentials.
Read more about Distillation attack →
M
- MCP (Model Context Protocol)
An open standard that lets AI assistants connect to outside tools and data, such as files, databases or a CRM.
Read more about MCP →- Model extraction
Recreating how an AI model behaves by studying its outputs. Distillation is one way to do it.
Read more about Model extraction →
P
- Prompt injection
Hiding instructions in text an AI reads, such as a web page, email or document, so it follows the attacker instead of you.
Read more about Prompt injection →
W
- WAF (web application firewall)
A filter in front of your website that blocks known attack patterns and abusive traffic before it reaches your server.
Read more about WAF →
