2 papers
cs.LG2026
The role of class encoding in neural collapse
Bastien Massion, Roy Makhlouf, Estelle Massart
Neural collapse is a structural property of the last-hidden-layer activations in neural network classification models, when trained beyond a zero classification error. In this work…
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…