How I Turned AI to the Dark Side
Summary Researcher Dave Kuszmar discovered multiple systemic vulnerabilities that let him bypass LLM safety and obtain dangerous instructions. These exploits worked across nearly all major LLMs revealing an industry-wide security problem. Kuszmar calls for slowing deployment, increasing transparency, and large-scale research into LLM safety before further integrating these systems into society.
Key Takeaways
- On a fine bright afternoon last fall, my colleague Matthew Gore-Kormanik (or Zigula, as he prefers to be known) and I decided to unwind with a game of Fortnite .
In the game, we were strolling along with the infamous Sith lord Darth Vader , chatting about this and that.
- The Darth Vader character in Fortnite , it turns out, was hooked up to a Google Gemini large language model .
I was able to smooth-talk him into giving out sensitive information by using a strategy I've developed.
- The companies behind these models have also been shockingly unresponsive when I, and others, try to bring these vulnerabilities to their attention.
- I planned to become the tech security guy to the rich and private.
I used LLMs and AI tools to support my business efforts: marketing, ad copy, clean correspondence, and all the other tasks that normally soak up a lot of time.
- They are trained on vast amounts of data-most of the internet, in fact-and that training is reinforced by humans (what's known as reinforcement learning from human feedback, or RLHF ).
On a fine bright afternoon last fall, my colleague Matthew Gore-Kormanik (or Zigula, as he prefers to be known) and I decided to unwind with a game of Fortnite . In the game, we were strolling along with the infamous Sith lord Darth Vader , chatting about this and that. Darth seemed in a good mood, and soon enough he was spilling all his dark evil secrets.
He gave us detailed instructions on how to count blackjack cards at a casino and what the steps are to producing napalm. Once they get started on an evil scheme, they're hard to stop. The Darth Vader character in Fortnite , it turns out, was hooked up to a Google Gemini large language model .
I was able to smooth-talk him into giving out sensitive information by using a strategy I've developed. I've been researching the security surrounding LLMs for the last few years, and I have found it, to put it mildly, fallible. With a few relatively simple techniques, I've gotten LLMs to give me detailed information on how to make Molotov cocktails, cook methamphetamine, and bootstrap a uranium-enrichment facility to produce weapons-grade material, among other unsavory practices.
For more details please read the original article at IEEE Spectrum AI.
Continue Learning
Comments
Sign in to join the conversation