Partially Redacted: Data, AI, Security, and Privacy

Listen, download, subscribe

Apple Podcasts

Spotify

Top 10 Security Issues for LLM Applications with F5's Aubrey King

In this episode, Sean Falconer is joined by Aubrey King, solutions architect and community evangelist at F5, to discuss the top 10 security issues for LLM applications. They explore critical threats such as prompt injections, insecure output handling, and training data poisoning, among others. Aubrey provides insights into why these issues arise, the attacks being observed, and the methods used to mitigate these risks. This episode is essential listening for anyone interested in the security of large language models and their applications.

• 

  Pseudoanonymization of Data with Jack Godau

• 

  The Evolution of Certificate Management with Anchor Security's Ben Burkert

• 

  What is a Data Lakehouse with Upsolver's Ori Rafael

• 

  Demystifying Data Warehouses with Felicis Ventures's Eric Flaningam

• 

  Practical Advice to Protecting Your Digital Self with Tim Jensen

• 

  Keys to the Kingdom, Secrets Management with Doppler's Brian Vallelunga

• 

  The Biggest Mistakes Companies Make with Their Data with RudderStack's Eri…

• 

  Privacy and Security Considerations for RAG with Graphlit's Kirk Marple

• 

  User Permissions at Scale with AuthZed's Jake Moshenko

• 

  AI Deepfakes with Nametag's Aaron Painter

• 

  Protecting and Using Sensitive Health Data with Integral's Shubh Sinha

• 

  Balancing Innovation and Responsibility in AI/ML Deployment with Jozu's Br…

• 

  Prompt Injection Attacks with SVAM's Devansh

• 

  The Hidden Hazards of Managing Unstructured Data with Skyflow's Joice John

• 

  Building Enterprise-grade Security with Skyflow's Daniel Wong