Minimal and annotated implementations of key ideas from modern deep learning research.
Awesome LLM pre-training resources, including data, frameworks, and methods.
Finetune ALL LLMs with ALL Adapeters on ALL Platforms!
A curated list of useful resources that cover Offensive AI.
Repository accompanying a paper on Red-Teaming for Large Language Models (LLMs).
Adversarially robust phishing email detection using DistilBERT, adversarial training, and a real-time Gradio interface.
Curated reading list for adversarial perspective and robustness in deep reinforcement learning.
Framework for testing vulnerabilities of large language models (LLM).
Red AI Range (RAR) is a security platform for AI red teaming and vulnerability assessment using Docker.
Targeted Adversarial Examples on Speech-to-Text systems.
A CLI that provides a generic automation layer for assessing the security of ML models.
