pytorch-cnn-adversarial-attacks
Pytorch implementation of convolutional neural network adversarial attack techniques
- 364
- Python
- MIT
- 8 y ago
Pytorch implementation of convolutional neural network adversarial attack techniques
CLIP GUI - XAI app ~ explainable (and guessable) AI with ViT & ResNet models
CLIP Interrogator, fully in HuggingFace Transformers 🤗, with LongCLIP & CLIP's own words and / or *your* own words!
Use CLIP to create matching texts + embeddings for given images; useful for XAI, adversarial training
Get CLIP ViT text tokens about an image, visualize attention as a heatmap.
Head-Hunter: A Visual Bias Explorer. Attention Head Max Visualization to find, rank, and visualize heads; map bias; see what a CLIP 'sees'.
Classic original Inception style DeepDream, but with CLIP ResNet. And CLIP ViT for comparison.
Gradient Ascent for Text Encoders of CLIP-like models, including CLIP, BLIP, SigLIP, LLM2CLIP. Get a model's 'opinion' tokens about an image.
Like Golden Gate Claude, but with a CLIP Vision Transformer ~ feature activation manipulation fun!