AIRed Teaming
AI red teaming is the practice of systematically probing an AI system — typically a large language model or generative AI product — for security vulnerabilities, safety failures, and harmful behaviors before and after deployment, using adversarial techniques similar to traditional cybersecurity red teams.
3 resources across 1 library
Glossary Terms(3)
Prompt Injection
Prompt injection is an attack technique where crafted input manipulates a large language model into ignoring its original instructions or safety constraints an…
Jailbreak
In the context of AI, a jailbreak is a prompting technique or crafted input designed to bypass an LLM's built-in safety training and content policies, coaxing…
AI Red Teaming
AI red teaming is the practice of systematically probing an AI system — typically a large language model or generative AI product — for security vulnerabilitie…