dentangle, 23 days ago @mishari "We show an adversary can extract gigabytes of training data from open-source language models like Pythia or GPT-Neo, semi-open models like LLaMA or Falcon, and closed models like ChatGPT" https://arxiv.org/abs/2311.17035
@mishari "We show an adversary can extract gigabytes of training data from open-source language models like Pythia or GPT-Neo, semi-open models like LLaMA or Falcon, and closed models like ChatGPT"
https://arxiv.org/abs/2311.17035
baldur
falken