56 citations · 154 across the 19 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
Unintended memorisation of unique features in neural networks
John Hartley, Sotirios A. Tsaftaris
Neural networks pose a privacy risk due to their propensity to memorise and leak training data. We show that unique features occurring only once in training data are memorised by d…
cs.LG2022★ 5 cited
Measuring Unintended Memorisation of Unique Private Features in Neural Networks
John Hartley, Sotirios A. Tsaftaris
Neural networks pose a privacy risk to training data due to their propensity to memorise and leak information. Focusing on image classification, we show that neural networks also u…