activity
20232025
most citedReconstructing Training Data from Multiclass Neural Networks

3 citations · 3 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2025

Querying Kernel Methods Suffices for Reconstructing their Training Data

Daniel Barzilai, Yuval Margalit, Eitan Gronich +3

Over-parameterized models have raised concerns about their potential to memorize training data, even when achieving strong generalization. The privacy implications of such memoriza…

cs.LG2024

On the Reconstruction of Training Data from Group Invariant Networks

Ran Elbaz, Gilad Yehudai, Meirav Galun +1

Reconstructing training data from trained neural networks is an active area of research with significant implications for privacy and explainability. Recent advances have demonstra…

cs.LG2024

Reconstructing Training Data From Real World Models Trained with Transfer Learning

Yakir Oz, Gilad Yehudai, Gal Vardi +3

Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restricti…

cs.LG2024

MALT Powers Up Adversarial Attacks

Odelia Melamed, Gilad Yehudai, Adi Shamir

Current adversarial attacks for multi-class classifiers choose the target class for a given input naively, based on the classifier's confidence levels for various target classes. W…

cs.LG2024

RedEx: Beyond Fixed Representation Methods via Convex Optimization

Amit Daniely, Mariano Schain, Gilad Yehudai

Optimizing Neural networks is a difficult task which is still not well understood. On the other hand, fixed representation methods such as kernels and random features have provable…

cs.LG20233 cited

Reconstructing Training Data from Multiclass Neural Networks

Gon Buzaglo, Niv Haim, Gilad Yehudai +2

Reconstructing samples from the training set of trained neural networks is a major privacy concern. Haim et al. (2022) recently showed that it is possible to reconstruct training s…