1 code implementation • 31 Jul 2023 • Albert Yu Sun, Eliott Zemour, Arushi Saxena, Udith Vaidyanathan, Eric Lin, Christian Lau, Vaikkunth Mugunthan
In this work, we simulate a privacy attack on GPT-3 using OpenAI's fine-tuning API.
no code implementations • 27 Apr 2023 • Albert Yu Sun, Varun Nair, Elliot Schumacher, Anitha Kannan
We use CONSCENDI to exhaustively generate training data with two key LLM-powered components: scenario-augmented generation and contrastive training examples.