Lessons Learned from Developing Secure AI Workflows

Posted on in Presentations

This talk will discuss the Google Security AI Framework (SAIF), which is used to protect AI systems and workflows. Through concrete examples, presenters will cover the key threats that must be addressed when deploying AI systems and what mitigations to put in place with a focus on when to extend existing systems versus adding AI specific protections.

Elie Bursztein


Google & DeepMind AI Cybersecurity Technical and Research Lead, Google DeepMind

Share With Your Community