Wednesday
Room 4
16:20 - 17:20
(UTC+02)
Talk (60 min)
From Text to Flaws: vulnerabilities in applications with Generative AI and LLMs
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
Paul Molin
Paul Molin is the CISO of the Theodo Group.
After training in information systems security at Télécom ParisTech, he joins Theodo in 2013 and becomes passionate about web development. Very quickly, he specializes in security issues by helping Theodo teams to succeed in their post-production audits. He eventually becomes group CISO, and he is committed to creating a security culture in a developer company. He loves giving talks, especially to help developers understand the cybersecurity world. Convinced that it is developers who will change the world of cybersecurity, he leads trainings and develops tools to help them code flawlessly the first time.