
AppSec Aus Melb #24 - Securing the AI Supply Chain
About this event
Event Confirmation Form! ➡️ We kindly request you fill out this event confirmation form to confirm your attendance for the event and your dietary requirements - https://forms.gle/zExLfJdzJcuvYyXM8 \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- What's On? 👀 Speaker: Griffyn Hancock (https://www.linkedin.com/in/ACoAADTVplQBeE7_iPXtuCbX4JnTPQuYJ15TV58/) Title: Can You Trust That Model? Securing the AI Supply Chain Abstract: This talk will examine practical threats across the AI supply chain, including: • Malicious model files and unsafe deserialisation • Risks introduced by downloaded and locally hosted models • Securing MCP servers and other tools connected to AI systems • Misconfigurations that may expose credentials or sensitive data • “Sleeper agent” models that behave maliciously only when particular conditions are met We’ll look at where these risks enter the development lifecycle, how they differ from familiar software supply-chain threats, and what teams can do to evaluate models and supporting tools before using them. The session is intended for security practitioners, engineers and anyone involved in building or operating AI systems. No specialist machine-learning knowledge is required. Location 📍 Atlassian Melbourne Queens & Collins Building, Level 20, 100 Queen Street, Melbourne VIC 3000 Agenda ⏰ • 5:30 - Food is served • 6:15 - Session start • 7:30 - Post-event networking \-\-\- Note: Please complete the event confirmation form: https://forms.gle/zExLfJdzJcuvYyXM8
Questions & comments
Ask the host anything — replies are visible to everyone.
—