From Text to Flaws: vulnerabilities in applications with Generative AI and LLMs - Paul Molin

This talk was recorded at NDC Oslo in Oslo, Norway. #ndcoslo #ndcconferences #developer #softwaredeveloper Attend the next NDC conference near you: https://ndcconferences.com https://ndcoslo.com/ Subscribe to our YouTube channel and learn every day: / @NDC Follow our Social Media! https://www.facebook.com/ndcconferences https://twitter.com/NDC_Conferences https://www.instagram.com/ndc_conferences/ #security #ai #chatgpt #ndcoslo #ndcconferences With the advent of ChatGPT and LLMs, a new world of possibilities has opened up in tech. The first use cases were quick to follow: new applications based on generative AI are being deployed in production every day. In this brand-new field, the race has begun between developers and security experts on the one hand, and attackers on the other. What are the risks of applications using LLMs? What practical means do developers have to protect themselves? This is what I'm going to talk about in this talk, explaining: - how LLMs and the applications that leverage them work - typical vulnerabilities in applications using generative AI (with juicy stories to back it up) - countermeasures developers can take to protect their applications