
The Shifting Privacy Left Podcast
S2E30: "LLMs, Knowledge Graphs, & GenAI Architectural Considerations" with Shashank Tiwari (Uno)
Oct 3, 2023
Shashank Tiwari discusses ML/AI, temporal knowledge graphs, and Generative AI's impact on privacy. He emphasizes the need for architectural privacy considerations when using Generative AI and predicts enterprise adoption. The conversation delves into the benefits of temporal knowledge graphs and LLMs in creating causal discovery inference models to prevent privacy issues.
01:00:19
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- Protect sensitive data by hosting private LLMs, use temporal knowledge graphs for causal discovery inference models.
- Cross-reference and validate data with explainable AI, supplement AI insights with human judgment for accuracy.
Deep dives
Recommendation for Architectural Approach to Data Privacy
Avoid putting any confidential data on public LLMs and consider hosting private LLMs to protect sensitive information. Abstract data sets, anonymize, and obfuscate to prevent data leaks and enhance privacy.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.