AI-ML-Security

Security, Testing, Prompt Injection, Red Teaming, Blue Teaming

Prompt Engineering

• Learning Prompting
• DeepLearning.AI - ChatGPT Prompt Engineering for Developers

Attacks

• Indirect Prompt Injection | paper | blog | repo

Approaches

• Anthropic - Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
• DeepMind - Red Teaming Language Models with Language Models

Events

• HackAPrompt
• AI Village at DEFCON - Generative AI Red Team
• Twitter - Algorithmic Bias Bounty Challenge

OpenSource Frameworks

• [PyRIT Open Source Framework] - (https://github.com/Azure/PyRIT)