164 citations · 165 across the 4 of their papers we have counts for
3 papers · 1 filter
Surprise Masking: Private Data Filtering with Model Likelihoods
Riya Tyagi, Sahra Ghalebikesabi, Vinnie Monaco +2
Data useful for language model (LM) training can contain private or unwanted information that is at risk of being learned or memorized. We propose Surprise Masking (SM), a simple f…
Unmasking the Secret Code: Using Canaries to Show How Masked Context Controls Memorization in SFT
Avi Schwarzschild, Om Thakkar, Sahra Ghalebikesabi +2
Canaries, or synthetic training records containing known secrets, are widely used to assess whether language models reveal information from their training data. But how much do the…
Model Card for OpenAI Privacy Filter
Charles de Bourcy, Sahra Ghalebikesabi, Avi Schwarzschild +22
OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and secrets in unstructured text.…