Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?

arXiv:2307.16382v2 Announce Type: replace
Abstract: Machine learning practitioners often fine-tune generative pre-trained models like GPT-3 to improve model performance at specific tasks. Previous works, however, suggest that fine-tuned machine learning models memorize and emit sensitive information from the original fine-tuning dataset. Companies such as OpenAI offer fine-tuning services for their models, but no prior work has conducted a memorization attack on any closed-source models. In this work, we simulate a privacy attack on GPT-3 using OpenAI's fine-tuning API. Our objective …

api arxiv cs.cl cs.lg fine-tuning gpt gpt-3 information leak openai openai api type