The Anatomy of Attacks on LLMs
Prompts thefts, leakages, injections, jailbreaks and other exotic vulnerabilities to be aware of (and try out).
“AI is both a sword and a shield in cybersecurity. It enhances our ability to detect and respond to threats, yet it also escalates the complexity and sophistication of the attacks we must prepare for.”
— Bruce Schneier
Why do attacks on LLMs matter?
Well, as Bruce said, AI is a sword and a shield.
ChatGPT, Claude, LLaMa, and other open source models are now an essential part of our everyday life.
This article is written based on assumption that in the very very very very very near future:
On one hand, all of the companies will become AI or AI-enhanced companies. Every single business (doesn’t matter whether a single-person or a multimillion corp.) will have an AI factory.
On the other hand, all people will have some sort of AI agents for 99% of the tasks in the future. Starting from real-time translation agents that speak perfectly in your voice and tonality, which remove all imaginable barriers to speaking foreign languages, and finishing with the domestic robots that’ll do the majority of the tedious tasks like “cooking” and “cleaning” (this one will definitely take a while. The question of “Why?” I’ll…
