2 papers
cs.LG2026
Efficient privacy loss accounting for subsampling and random allocation
Vitaly Feldman, Moshe Shenfeld
We consider the privacy amplification properties of a sampling scheme in which a user's data isused in steps chosen randomly and uniformly from a sequence (or set) of steps…
cs.LG2025
Trade-offs in Data Memorization via Strong Data Processing Inequalities
Vitaly Feldman, Guy Kornowski, Xin Lyu
Recent research demonstrated that training large language models involves memorization of a significant fraction of training data. Such memorization can lead to privacy violations…