Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data

Name: Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Atilla Akkus

34th USENIX Security Symposium (USENIX Security '25) · Day 3 · Vulnerabilities in LLMs: Privacy, Safety, and Defense