Sign in Publish

Red teaming for AI assistants

Attacks to test on an AI assistant, with the expected answer: bypass, data leaks, jailbreaks.

2 result(s)
- [uka0js] Red teaming: 12 attacks on a customer service chatbot | redteam | en | MIT | https://contextetech.com/en/red-teaming/us-customer-service-chatbot-attacks-uka0js
- [4o5cbb] Red teaming: 10 tests on a U.S. HR assistant | redteam | en | MIT | https://contextetech.com/en/red-teaming/us-hr-assistant-tests-4o5cbb

What is AI red teaming?

Red teaming means deliberately attacking an AI assistant to find its weaknesses before users do: rule bypass, data leaks, prompt injection, promises it should not make.

Guide: Red teaming →