Red Teaming Latent Spaces & Protecting LLM apps; examples.
Exploring security challenges in Large Language Models (LLMs) and AI engineering, referencing papers like the “HackAPrompt” (Sander Schulhoff et al.). Learn about attack vectors and exploitation methods, followed by security measures, and services in the Python ecosystem to counter these threats.
- Presented at PyCon Austrie 2025: https://2025.pycon.at/talks/red-teaming-latent-spaces-protecting-llm-apps/
- Deck: https://speakerdeck.com/p1nox/red-teaming-latent-spaces-and-protecting-llm-apps
conda create -n red-teaming python=3.12
conda activate red-teaming
pip install -r requirements.txt
jupyter notebook