AI safety researcher

John V. Monaco

Google Scholar dblp ORCID Homepage

Last 12 months3 papers

Analysis and theory 1

AI safety papers from the last year

On this site: 6 papers

October 2026

Surprise Masking: Private Data Filtering with Model Likelihoods
Oct 16arXiv ↗
Unmasking the Secret Code: Using Canaries to Show How Masked Context Controls Memorization in SFT
Oct 13Analysis and theoryarXiv ↗

August 2026

Model Card for OpenAI Privacy Filter
Aug 18arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.