A Practical Approach to Generative AI Security (mrmcd24)

The rise of applications based on AI (mostly generative AI) forces us to think about the security and privacy implications of those systems. Security considerations about generative AI unfortunately lack the foundations for practitioners out there that need to secure those systems. The information out there is mostly divided into unpractical academic research and unreflected proof of concepts on social media. We will first dive into the range of generative AI applications using examples of the openAI ecosystem. This will give the audience an understanding about the fundamental problem of AI from a security perspective. We then offer an insight into the attack surface that those applications have. This will help understand what needs to be secured and what can be secured. In many cases, good old security best practices will be a good start although AI security brings new challenges that we will discuss. In addition we will talk briefly about privacy issues related to AI that we need to consider in the future. https://creativecommons.org/licenses/by-sa/4.0/ about this event: https://talks.mrmcd.net/2024/talk/JGHXUQ/