The Shifting Privacy Left Podcast cover image

S2E30: "LLMs, Knowledge Graphs, & GenAI Architectural Considerations" with Shashank Tiwari (Uno)

The Shifting Privacy Left Podcast

CHAPTER

Protecting Highly Confidential Data Sets

The chapter emphasizes the importance of safeguarding sensitive data like social security numbers, health records, and financial information when utilizing new language models, suggesting the use of filters and brokers to prevent data leaks. It explores options like hosting private language models for better data protection and addresses architectural considerations for handling confidential data securely. Additionally, it discusses the complexities of trust in AI systems, the challenges of ensuring fairness and bias mitigation, and the evolving landscape of AI security threats and preventive measures.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner