TextAttack is a Python framework for adversarial attacks, data augmentation, and model training in NLP.
A controllable SONAR image generation framework utilizing text-to-image diffusion and GPT prompting for enhanced diversity and realism.
Open-source LLM Prompt-Injection and Jailbreaking Playground for evaluating LLM security vulnerabilities.
Discover the leaked system instructions and prompts for ChatGPT's custom GPT plugins.
Guard your LangChain applications against prompt injection with Lakera ChainGuard.
Application which investigates defensive measures against prompt injection attacks on LLMs, focusing on external tool exposure.
Fine-tuning base models to create robust task-specific models for better performance.
This repository contains the official code for the paper on prompt injection and parameterization.
Implementation of the PromptCARE framework for watermark injection and verification for copyright protection.
A writeup for the Gandalf prompt injection game.
Uses the ChatGPT model to filter out potentially dangerous user-supplied questions.
Custom node for ComfyUI enabling specific prompt injections within Stable Diffusion UNet blocks.
