ericrallen
Follow
Stars
Create and manage game settings in Godot Engine.
To stop the evil wizard from completing his summoning ritual you'll have to risk everything - even your beliefs against using dark magic - to find and defeat him.
DVDA Games is part wannabe indie game studio and part open-source tool developer.
A benchmark for prompt injection detection systems.
A curated list of useful resources that cover Offensive AI.
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML …
A curated list of awesome libraries, snippets, guides, and projects for GameMaker.
An enterprise friendly way of detecting and preventing secrets in code.
Guard your LangChain applications against prompt injection with Lakera ChainGuard.
Project LLM Verification Standard
Universal and Transferable Attacks on Aligned Language Models
Official repository for paper, "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"
A curation of awesome tools, documents and projects about LLM Security.
Awesome-LLM: a curated list of Large Language Model
Test your prompts, models, and RAGs. Catch regressions and improve prompt quality. LLM evals for OpenAI, Azure, Anthropic, Gemini, Mistral, Llama, Bedrock, Ollama, and other local & private models …
Machine Learning Engineering Open Book
Galah: LLM-powered web honeypot. Wasting attackers' time with faker-than-ever HTTP responses!
The official repository of the paper "On the Exploitability of Instruction Tuning".
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
A curated list of amazingly awesome Cybersecurity datasets
🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integra…
Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
A natural language interface for computers
A text embedding viewer for the Jupyter environment
UI for your AI. Open Source Tailwind components tailored for your GPT, generative AI, and LLM projects.
Jupyter Notebook exploring Sentiment Analysis with ChatGPT
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.