Red Teaming LLMs // Ron Heichman // #252

MLOps.community

Ron Heichmn is an AI researcher specializing in generative AI, AI alignment, and prompt engineering. At SentinelOne, Ron actively monitors emerging research to identify and address potential vulnerabilities in our AI systems, focusing on unsupervised and scalable evaluations to ensure robustness and reliability.

Harnessing AI APIs for Safer, Accurate, & Reliable Applications // MLOps Podcast #252 with Ron Heichman, Machine Learning Engineer at SentinelOne.

// Abstract

Integrating AI APIs effectively is pivotal for building applications that leverage LLMs, especially given the inherent issues with accuracy, reliability, and safety that LLMs often exhibit. I aim to share practical strategies and experiences for using AI APIs in production settings, detailing how to adapt these APIs to specific use cases, mitigate potential risks, and enhance performance. The focus will be testing, measuring, and improving quality for RAG or knowledge workers utilizing AI APIs.

// Bio

Ron Heichman is an AI researcher and engineer dedicated to advancing the field through his work on prompt injection at Preamble, where he helped uncover critical vulnerabilities in AI systems. Currently at SentinelOne, he specializes in generative AI, AI alignment, and the benchmarking and measurement of AI system performance, focusing on Retrieval-Augmented Generation (RAG) and AI guardrails.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

Website: https://www.sentinelone.com/

All the Hard Stuff with LLMs in Product Development // Phillip Carter // MLOps Podcast #170: https://www.youtube.com/watch?v=DZgXln3v85s&ab_channel=MLOps.community

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Ron on LinkedIn: https://www.linkedin.com/in/heichmanron/

Timestamps:

[00:00] Ron's preferred coffee

[00:20] Takeaways

[01:08] Register now for the Data Engineering for AIML Conference!

[01:59] AI vs ML Solutions

[05:42] AI Application challenges

[09:38] AI Model evolution

[19:22] AI tools accessibility challenge

[20:53] AI tools accessibility gap

[24:00] Optimizing LLM Performance

[30:31] Red teaming taxonomy

[36:11] Securing custom LLMs

[44:32] Diverse data in LLMs

[46:29] Automated data diversity feedback

[50:42] Model stress-testing process

[55:49] Early issue detection benefits

[57:41] Prompt injection patterns

[1:02:11] Best jailbreaks seen by Ron

[1:04:53] Data poisoning vulnerabilities

[1:07:48] Wrap up