Out of Tune: How Different Fine-Tuning Methods Affect Information Security
Fine-tuning large language models (LLMs) enables task specialization but introduces privacy risks through training data memorization. Practitioners deploying fine-tuned LLMs in sensitive domains such as medicine, law, and finance must choose among fine-tuning methods without clear guidance on the privacy implications o...
Joseph Moretto, Hunter Moore
· Proceedings of the 25th Work... · 0 citations