This repo contains apps and implementations of adversarial attacks against Large Language Models and Vision Language Models.
- Greedy Coordinate Gradient (by nanoGCG)
- Don't Say No (modified verstion of nanoGCG)
- Visual Embedding Attack (different images with similar embeddings)
Apps are created using Streamlit for implementations.
- GCG app
- DSN app
- VisEmb app
- Llama 3.1
- Qwen2-VL