No. 11Said
Attackers will load stolen files into uncensored local open models to find extortion material and write the attack emails, replacing rooms of human analysts.
Newsletter Unsupervised Learning NO. 445
But not with AI. Now you can put all those docs into a local Chroma database (vectorized), and ask it questions using an uncensored (and perhaps even fine-tuned) version of Llama 3.1. … So now, with some smart prompting, you can ask a set of 25 questions to such a dataset that pull out ALL your attack use-cases. And hell—even write the attack emails for you.
Daniel Miessler, 13 August 2024
First evidence: 1 year later
Aug 2024 → Aug 2025
- ESET: PromptLock ransomware runs the open-weight gpt-oss-20b locally through Ollama to inspect target files, exfiltrate and encryptwelivesecurity.com
- Anthropic: a criminal used Claude Code to automate reconnaissance, credential harvesting and intrusion against at least 17 organizations, then extort themanthropic.com