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