LLM Privacy Paradox: Balancing Data Utility...

LLM Privacy Paradox: Balancing Data Utility with Security Rob Ragan, Aashiq Ramachandran Advancements in LLMs have prompted individuals and companies to fine-tune their own for specialized use cases. The million-dollar question is, when I fine-tune...

LLM Privacy Paradox: Balancing Data Utility with Security

Rob Ragan, Aashiq Ramachandran

Advancements in LLMs have prompted individuals and companies to fine-tune their own for specialized use cases. The million-dollar question is, when I fine-tune an LLM with my sensitive data (PII, PHI, FII, etc.), do I risk the tuned model leaking data or not?

https://bsidessf2024.sched.com/event/6c23df632120d54cc505132f3ac4499f