Ai-Security

When the Fideuram fraud hit the news on Friday, my first thought was: I’ve read this one before. A WhatsApp message from an unknown number claiming to be the boss, a confidential deal, a lawyer vouching for it, money that has to move to Asia fast. It was the same script as the attempt against Ferrari in July 2024.

For the first two weeks I spent studying prompt injection I did the wrong thing: I collected prompts. I would read a thread, find a phrasing that had worked against some model, and paste it into my notes. I ended up with a sixty-line file that explained nothing. Sixty one-off cases.