How to Attack and Defend LLMs: AI Security Explained
Join us for this public, free seminar. Morning tea will be served after the seminar ends at 11am. Please register so we have numbers for catering.
Abstract
Ready to dive into the world of large language models (LLMs)? Whether you're a cybersecurity enthusiast, a data scientist, or a beginner with a curiosity for how LLMs can be hacked and protected, this seminar will give you the insights you need to stay ahead of the game.
Disclaimer: This seminar is for educational purposes only. We do not encourage or support any illegal activity. The techniques discussed are meant to highlight security vulnerabilities and help individuals enhance their own cybersecurity awareness. Always obtain proper authorisation before engaging in any form of testing or assessments.
What You'll Learn: From understanding how hackers exploit language models to building defences, this talk will guide you through the critical concepts of LLM security. Learn how adversarial attacks work and how to safeguard your own models from being manipulated.
Key Topics Covered:
Understanding Language Model Vulnerabilities: Explore how attackers exploit weaknesses in LLMs to manipulate outputs or extract sensitive data.
Common Hacking Techniques: Learn about techniques like prompt injection, backdoor attacks, and how they impact model security.
Adversarial Attacks & Mitigation: Discover how adversarial examples are used to fool models, and the cutting-edge defences to protect against them.
Protecting Your Models: Practical tips on how to secure your LLMs from data leaks, model inversion, and other threats.
Securing Large-Scale Models: Best practices for deploying and maintaining large models in a secure environment, including model testing and monitoring.
This seminar is ideal for AI researchers, cybersecurity professionals, and anyone interested in the intersection of artificial intelligence and security. Empower yourself with the knowledge to build robust, secure models and stay one step ahead of potential threats.
About the speaker
Holly Wright is an architect and software engineer in the IBM Security team. She has expertise across many domains in cyber-security, with focus areas in AI, threat detection and digital identity. She leads global teams in building software that keeps the world more secure.
Holly won "Best Female Secure Coder" at the 2022 Australian Women in Security awards and has five patents with the US patent office.
Holly is passionate about encouraging people into STEM and is part of many university and school mentoring initiatives.