Cloud Security Podcast by Google
EP136 Next 2023 Special: Building AI-powered Security Tools - How We Do It?
Aug 28, 2023
Eric Doerr, VP of Engineering at Google Cloud Security, discusses the exciting prospects of using AI for security and trusting AI in the business context. They also explore threat modeling AI systems and the worst security use cases for GenAI. Teaching AI security and the surprising challenges involved are also covered.
21:31
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- Teaching AI to understand and apply security principles is crucial for enhancing its performance in specific security use cases.
- Incorporating generative AI into security products and building an AI platform for security use cases can fill the gap in the market and enable individuals and organizations to protect their infrastructure effectively.
Deep dives
Teaching AI for Security
The podcast discusses the importance of teaching AI to understand and apply security principles. The guest explains that while foundational AI models are impressive, they may not perform well in specific security use cases due to the lack of proprietary information in the training data. To address this, the guest shares how they feed specific information into the AI models to fine-tune and enhance their security capabilities. The ongoing process involves working with partners and incorporating relevant data to ensure the AI understands and speaks the language of various security domains.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
