LLM (Large Language Models)

# Prompting + Defensive Measures

Learn Prompting: Your Guide to Communicating with AI

# Types of Prompt Injections

Understanding Direct and Indirect AI Prompt Injections and Their ImplicationsEmbrace The Red

1. Direct Prompt Injections

2. Second Order Prompt Injections (aka Indirect Prompt Injections)

3. Cross-Context AI Injections

# Copied Prompt Injection PoC

https://prompt-injection.onrender.com/prompt-injection.onrender.com

# Insecure Response Processing [Data Exfiltration]

Do not blindly trust LLM responses. Threats to chatbots.Embrace The Red

# AI hallucinations

Can you trust ChatGPT’s package recommendations?Vulcan Cyber

# Testing Frameworks [To-Do]

1. Giskard

GitHub - Giskard-AI/giskard: Quality Assurance for AIGitHub

1. langflow

GitHub - logspace-ai/langflow: ⛓️ Langflow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.GitHub

# Jailbreaking Chat/ Do Anything Now (DAN)

Jailbreak Chat

# Threat Modelling

Threat Modeling LLM ApplicationsAI Village