HopeADeff/Hope
For protecting/preventing AI to mimic everyone's arts
Integrates Nightshade and Glaze adversarial perturbation techniques to poison training data for generative AI models, exploiting diffusion model latent spaces through convex optimization to induce concept corruption or style obfuscation. The system applies imperceptible noise modifications that preserve human visual perception while causing model mode collapse or semantic misalignment during fine-tuning. Targets Windows 10/11 systems and works with popular Stable Diffusion implementations, LoRA, and checkpoint-based models.
Stars
29
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/HopeADeff/Hope"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aloth/JudgeGPT
JudgeGPT: An empirical research platform for evaluating the authenticity of AI-generated news....
AkashKobal/Generative-AI-Detection
It aims to detect whether a given text or prompt is authored by a human or generated by an AI model.
chowfi/GenAI-image-detection
Detect AI-generated images in an online setting
Lyra-AI-Team/Trendyol-Hackathon
This repo contains Lyra AI's work in the E-Commerce Hackathon organized by Trendyol and Teknofest.
wehnsdaefflae/SpotTheBot
Spot The Bot tests players on their skill to spot AI-generated misinformation. Players identify...