Post Content
Welcome back to AI Red Teaming 101!
In this episode, Gary Lopez is joined by Nina Chikanov from Microsoft’s AI Red Team to demonstrate how to automate single-turn attacks using the open-source red teaming tool PyRIT. This hands-on walkthrough shows how to configure datasets, targets, scoring logic, and converters to run prompt injection attacks against generative AI models.
Nina walks through a real-world demo using PyRIT, showing how to evaluate model responses, apply token-level converters, and export results for analysis.
✅ Chapters:
00:00 – Welcome & episode overview
00:30 – Meet Nina Chikanov
01:00 – Review: what are single-turn attacks?
01:40 – Setting up a dataset in PyRIT
02:30 – Configuring memory labels and targets
03:30 – Connecting to Azure OpenAI endpoints
04:30 – Scoring model responses
05:30 – Using converters for token-level attacks
06:30 – Running the attack with PyRIT orchestrator
07:30 – Reviewing results and scoring outcomes
08:16 – Final thoughts & where to learn more
✅ Links & Resources:
AI Red Teaming 101 Episodes: aka.ms/airt101
AI Red Teaming 101 Labs & Tools: aka.ms/airtlabs
Microsoft AI Red Team Overview: aka.ms/airedteam
PyRIT GitHub Repository: https://github.com/Azure/PyRIT
✅ Speakers:
Amanda Minnich – Principal Research Manager, Microsoft AI Red Team
LinkedIn: https://www.linkedin.com/in/amandajeanminnich/
Webpage: https://www.amandaminnich.info/
Gary Lopez – Principal Offensive AI Scientist, ADAPT
LinkedIn: https://www.linkedin.com/in/gary-lopez/
Nina Chikanov – AI Red Team, Microsoft
LinkedIn: https://www.linkedin.com/in/nchikanov/
#AIRedTeam #AIRT #Microsoft #AI #AISecurity #AIRedTeaming #GenerativeAI #Cybersecurity #InfoSec #cybersecurityawareness #PromptInjection #PyRIT Read More Microsoft Developer
