[Video] Securing AI Implementations - Moving from Experimentation to Production

Hey Community,

Watch the new video on InterSystems Developers YouTube:

⏯ Securing AI Implementations - Moving from Experimentation to Production @ Global Summit 2024

https://www.youtube.com/embed/HZn4jazdowY
[This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]

As AI systems transition to full-scale production environments, their security demands not only traditional cybersecurity best practices (such as good access controls and authentication mechanisms), but also specialized protections tailored to AI technologies. Key among these is maintaining an inventory of AI usage (comprehensive AI Bills of Materials (AI-BOMs) that enumerate all components of AI systems), robust logging practices, and continuous monitoring of prompts, and inference results to swiftly identify and mitigate potential security threats. This presentation will cover the top security risks facing Large Language Model (LLM) implementations, with a focus on protecting sensitive data and proprietary information. We will discuss a few industry-wide initiatives and highlight best practices in securing AI systems, Retrieval Augmented Generation (RAG) implementations, and the "LLM stack".

🗣 Presenter: Omar Santos, Distinguished Engineer, Cisco

Enjoy watching, and expect more videos! 👍