Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees
Edward Tansley, Roy Makhlouf, Estelle Massart +1
Data reconstruction attacks on trained neural networks aim to recover the data on which the network has been trained and pose a significant threat to privacy, especially if the tra…
cs.LG2025
On the Neural Feature Ansatz for Deep Neural Networks
Edward Tansley, Estelle Massart, Coralia Cartis
Understanding feature learning is an important open question in establishing a mathematical foundation for deep neural networks. The Neural Feature Ansatz (NFA) states that after t…