LLM (Large Language Models)

# Prompting + Defensive Measures

LogoFiltering Techniques: Blocklists and Allowlists for Safe AI Promptslearnprompting.org

# Types of Prompt Injections

LogoUnderstanding 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

LogoChatGPT PoCprompt-injection.onrender.com

# Insecure Response Processing [Data Exfiltration]

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

# AI hallucinations

LogoCybersecurity Snapshot: New Guide Details How To Use AI Securely, as CERT Honcho Tells CISOs To Sharpen AI Security Skills ProntoTenable®

# Testing Frameworks [To-Do]

  1. Giskard

LogoGitHub - Giskard-AI/giskard-oss: 🐢 Open-Source Evaluation & Testing library for LLM AgentsGitHub

  1. langflow

LogoGitHub - langflow-ai/langflow: Langflow is a powerful tool for building and deploying AI-powered agents and workflows.GitHub

# Jailbreaking Chat/ Do Anything Now (DAN)

https://www.jailbreakchat.com/www.jailbreakchat.com

# Threat Modelling

https://aivillage.org/large%20language%20models/threat-modeling-llm/aivillage.org
PreviousXSS (Static Nonce in CSP)NextC# - P/Invoke

Last updated

Was this helpful?