[Webinar] Building LLM applications in a secure way (WithSecure™)

Показать описание

This is the recording of a webinar we did at WithSecure about the risks of creating LLM applications that act as autonomous agents, and what can be done to mitigate these risks.

Timestamps:
00:10 - Where did LLMs come from?
05:36 - Building LLM applications
06:52 - LLM agents
08:10 - Misconceptions about AI safety
09:58 - Risks of LLM use-cases
11:30 - Prompt injection (demo)
18:46 - LLM agents
24:00 - Prompt Injection Demo in Browser Agent (Taxi AI)
30:06 - Root cause of LLM alignement issues
34:45 - Comparison with traditional injection attacks
37:14 - Controls and defences against prompt injection
46:45 - Take-away points
49:32 - Questions

Donato Capitella

Рекомендации по теме

Комментарии

Great talk - thank you. I use LMMs every day - but I have never given them autonomy to take control over my systems or data (I promote semi-automation with human in the loop). Human+AI will be more difficult to hack than only AI or only Human.

micbab-vgmu

For the moment being, that's absolutely the way to go. I worry about some of the autonomous agents that are becoming all the rage in the media, I love them from a technical point of view and the engineers working at those startups are creative heroes, but we have done fundamental issues still to solve with the underlying tech.

donatocapitella

[Webinar] Building LLM applications in a secure way (WithSecure™)

[Webinar] Building LLM applications in a secure way (WithSecure™)

Webinar 'Best practices for building LLM-based applications'

LlamaIndex Webinar: Building LLM Apps for Production, Part 1 (co-hosted with Anyscale)

Building LLM applications with LangChain with Lance

How to Build Local LLM Apps with Ollama & SingleStore for Max Security | SingleStore Webinars

Building and Deploying LLM Applications with Apache Airflow

[Webinar] What's The Deal With LLM App Development in 2024?

Building Production-Grade LLM Apps

Build a NoCode LLM App

New Models and Features for Easily Building LLM-Based Applications with Superpowered AI

LLM App Dev for Beginners | Case Done Webinar

LlamaIndex Webinar: Building an LLM-powered Browser Agent

Developing Secure and Performant LLM Applications using Rust - Global AI Notes

Building Controllable and Reliable LLM Applications

ODSC Webinar | Preparing for your First Enterprise Large Language Model (LLM) Application

LlamaIndex Webinar: Build/Break/Test LLM Apps Showcase (co-hosted with TrueEra, Pinecone)

Webinar 'Building production ready LLMs with specialisation'

How to evaluate LLM Applications - Webinar by deepset.ai

Emerging architectures for LLM applications

Developing and Serving RAG-Based LLM Applications in Production

Evaluating LLM-based Applications

Webinar - Agent Based LLM Applications: Separating the Hype from Practical Applications

[WEBINAR] Optimizing LLM Applications with Retrieval Augmented Generation (RAG)

Building RAG-based LLM Applications for Production // Philipp Moritz & Yifei Feng // LLMs III Ta...