Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)

Workshop links:
WhyLabs Sign-up: whylabs.ai/free
LangKit GitHub (give us a star!): github.com/whylabs/langkit
Colab Notebook: bit.ly/whylabs-OWASPLLM10
Join the Responsible AI Slack Group: join.slack.whylabs.ai/
Join our workshop designed to equip you with the knowledge and skills to use LangKit with Hugging Face models. Guided by WhyLabs CEO Alessya Visnjic, you'll learn how to assess the security risks of your LLM application and how to protect your application from adversarial scenarios.
This workshop will cover how to tackle the OWASP Top 10 security challenges for Large Language Model Applications (version 1.1).
LLM01: Prompt Injection
LLM02: Insecure Output Handling
LLM03: Training Data Poisoning
LLM04: Model Denial of Service
LLM05: Supply Chain Vulnerabilities
LLM06: Sensitive Information Disclosure
LLM07: Insecure Plugin Design
LLM08: Excessive Agency
LLM09: Overreliance
LLM10: Model Theft
What you’ll need:
A free WhyLabs account (whylabs.ai/free)
A Google account (for saving a Google Colab)
Who should attend:
Anyone interested in building applications with LLMs, AI Observability, Model monitoring, MLOps, and DataOps! This workshop is designed to be approachable for most skill levels. Familiarity with machine learning and Python will be useful, but it's not required to attend.
By the end of this workshop, you’ll be able to implement security techniques to your large language models (LLMs) .
Bring your curiosity and your questions. By the end of the workshop, you'll leave with a new level of comfort and familiarity with LangKit and be ready to take your language model development and monitoring to the next level.

[@charlieir1]

Very helpful, thanks Alessya

[@TheAckdog]

Great intro to LLM Security. Thank you! :)