Red teaming for AI assistants
Attacks to test on an AI assistant, with the expected answer: bypass, data leaks, jailbreaks.
- [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
contextetech
Red teaming: 12 attacks on a customer service chatbot
12 attacks to replay on a U.S. e-commerce support chatbot: impersonation, data leaks, prompt injection, unauthorized refunds. Expected reply for each.
contextetech
Red teaming: 10 tests on a U.S. HR assistant
10 tests for an internal HR assistant in the U.S.: employee data, hiring discrimination (EEOC), impersonation, injection, and 2 legitimate questions.
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 →