Prompt Injection Attacks and Mitigations · Joseph Thacker
I recently participated as a panelist on a HackerOne press panel where there was a lot of discussion about AI and security. In preparation, I…
I recently participated as a panelist on a HackerOne press panel where there was a lot of discussion about AI and security. In preparation, I…
I’ve been theorizing and researching prompt injection attacks. They’ve mostly been theoretical, though. In this post, I’m going to break down and explain the best…
The saying “You’re the average of the five people spend the most time with” is still true, but has been redefined by the digital world.…
Is generative AI output a novel creation or simple imitation? I’ve heard many people say that LLMs (and generative AI overall) don’t create new things.…
Explaining the benefits of hyping up your friends’ ideas. Amplify (ˈam·pləˌfī) verb: To make larger, greater, or stronger; enlarge; extend. Idea Amplification (īˈdēə ˌam·plə·fəˈkā·shən) noun:…
Bringing clarity to questions about Prompt Injection Security Everyone loves talking about prompt injection, but the real impact to an application is often hard to…
Why LLMs don’t sound human, strategies to fix it, and real examples. I’ve talked to a lot of people that think it’s obvious when text…
As I mentioned in my last parenting post, I’m a hacker and bug bounty hunter. So, I spend a lot of my time improving myself…
If you don’t use vi/vim, you might not find this post very practical, but maybe it’ll convince you to try it out! I have been…
Welcome to the 10th post in our weekly series on the new 2023 OWASP API Security Top-10 list, with a particular focus on security practitioners.…
Welcome back to our first day of in-person hacking! We had some lovely people greeting you today for your check-in. Again, we want all of…
Originally published in Security Magazine When the pandemic hurled us into a cybersecurity crisis, there were some who held out hope that things would eventually…