AI Security
What is LLM Security?
Also known as: AI Application Security
LLM security is the practice of identifying and mitigating risks specific to applications that use large language models, including prompt injection, insecure output handling, sensitive information disclosure, and supply chain issues. It matters because AI features introduce new attack surfaces that traditional application security testing does not fully cover.
Example
A review of a chatbot finds that model output is inserted into a web page without sanitization, creating a cross-site scripting risk.
Reference: OWASP ↗
Related Clear Infosec services
Related terms
Have a question about llm security in your environment? Talk to our team.