StoryFirst seen

Training AI on real attack data could make it better at hacking

A hacker group reportedly wants to train an open model on large amounts of real attack data to boost its intrusion skills.

Archived Updated

Everything it touches

0 names 1 voices 1 source posts

The story’s neighborhood

NAMESVOICESPOSTS

Explore the graph, or choose a connection below.

Follow the evidence

The source posts

This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.

PrathamLead source
Quick explainer for anyone confused about why this is scary. AI models can be trained further on specific data to get really good at a specific job. That’s called post-training. Jun is saying a hacker group wants to train an open model on a huge pile of real attack data, so the AI gets very good at breaking into systems. His own security project used a tiny fraction of that data and already beat the big frontier models. So imagine what a model trained on 100x more could do. It could find and use weaknesses in software faster than most defenders can fix them. This is why AI security needs way more attention right now.
Read original on X

How the headline evolved

  1. Training AI on real attack data could make it better at hacking

  2. Post-training on attack data could make AI better at hacking

  3. Post-training on attack data could make AI better at hacking

  4. Post-training on attack data could make AI better at hacking

  5. Post-training on attack data could make AI better at hacking