Skip to main content

AI Security 
Glossary

Get familiar with key terms and concepts in the AI Security space.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Denial of Wallet / Denial of Service

Denial of Wallet and Denial of Service attacks exploit the fact that every call to an LLM costs time, compute, or money, letting an attacker degrade service for legitimate users or run up a significant bill.

EU AI Act

The EU AI Act is the European Union's foundational law governing the development and use of AI, and the first comprehensive AI-specific regulation of its kind.

Hallucination

An AI hallucination is when a model produces a response that sounds fluent and confident but is factually incorrect or fabricated, a risk that gets more serious once an agent acts on that output instead of a person just reading it.

Indirect Prompt Injection

Indirect prompt injection happens when an LLM or agent processes attacker-controlled content from an external source, like a webpage or document, rather than a direct user input.

Insecure Plugin Design

LLMs and agents calling external tools, whether through legacy plugins, function calling, or MCP servers, can be manipulated into making malicious requests to those tools if inputs aren't properly validated.

ISO/IEC 42001

ISO/IEC 42001 is the first international standard for managing AI systems responsibly, covering governance, risk, and continuous improvement across an organization's AI use.

Jailbreak

Jailbreaking is a category of prompt injection focused on getting a model to ignore its safety training and guardrails rather than hijacking it for a specific downstream action.

Large Language Models (LLMs)

Large language models (LLMs) are AI systems trained on vast amounts of text to understand context and generate coherent language, and increasingly, to call tools and take action as the reasoning engine behind autonomous agents.

Model Context Protocol Gateway (MCP Gateway)

An MCP Gateway gives organizations centralized visibility and control over every MCP server and interaction in their environment, including the unauthorized ones.

Model Context Protocol (MCP)

Model Context Protocol (MCP) is an open standard, originally developed by Anthropic, for connecting LLMs to external tools, systems, and data sources through a single interface rather than custom integrations for every connection.

Model Context Protocol Server (MCP Server)

An MCP server is the component that gives an AI model or agent the ability to actually do something, read a file, call a function, run a command, rather than just talk about it.

Privilege Escalation

As LLMs and agents connect to more internal systems and MCP servers, the risk grows that those integrations are used, deliberately or not, to gain access beyond what was intended.