whitecircle/rise

Anti-DreamBooth: Protecting users from personalized text-to-image synthesis (ICCV 2023)

A collection of resources on attacks and defenses targeting text-to-image diffusion models

image scaling attacks for multi-modal prompt injection

YiJian-Comunity: a full-process automated large model safety evaluation tool designed for academic research

Train high-quality text-to-image diffusion models in a data & compute efficient manner

Provides a collection of sandboxes, exploitation code, and tutorials that exemplifies GenAI Red Teaming exercises. It aims to help security researchers and developers test, probe, and evaluate the safety and security of GenAI-based applications.

A crowdsourced distributed cluster for AI art and text generation

is an elite, highly advanced command-line framework designed for generating complex prompt structures. It is built to push the boundaries of AI models by testing their alignment, safety filters, and operational limits. By utilizing state-of-the-art obfuscation techniques, multi-layered theoretical bypass architectures, and linguistic fusion

[Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation