Archive
Industrial Series - Don't use LLMs
LLM safety and CS Lewis
Putting the 'I' in CIA for AI Models: A Framework for Model Integrity
Malicious ML series - generate ELF training data
Malicious ML series - VAE to generate binaries
Malicious ML series - GAN to generate binaries
Gradient Descent Adversarial Attacks
Attacking a simple Image Classifier from scratch
Attacking AI