AI and Cyber convergence topics.
In heavy industry (oil refineries, nuclear plants, or chemical facilities) AI promises efficiency but introduces unprecedented risks. As discussed in our series’ introduction, large language models (LLMs) can struggle when making numerical and logica...
As far as industrial engineering goes, I'm not saying don't ever use LLMs: I'm saying don't use them yet. LLMs are good at text; they're bad with numbers. They're not particularly well suited to combinations of text and numbers as seen in logic probl...
I was recently asked what I thought of LLM safety, and specifically how to move the cybersecurity community towards recognizing and finding related flaws. Beyond the obvious tactical techniques (prompt injection testing), I wanted to think through th...
We're missing a piece of the security puzzle
Purpose If we want to train an ML algorithm to produce something malicious - say, a C2 beacon or a ransomware binary, we need good training data. Approach Use MSFVenom to generate a few thousand samples we can then feed into an ML algorithm. Drawback...
Brute Variational Autoencoder In this approach, we use a VAE to generate entire binaries. This 'brute' approach is an experiment to see if it can generate functional binaries. Although unlikely to work, it will be interesting to see how far we can g...
Brute Generative Adversarial Network In this approach, we use a GAN to generate entire binaries. GANs sound perfect - they try and generate a binary from some noise, use a discriminator to find out if it was correct, and then goes back and tries aga...
Unraveling Gradient Descent with examples
Assemble and evaluate a simple machine learning model
