Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Haim, Niv"'
Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restrictions hinder their applicability to real-world scenarios. In this paper,
Externí odkaz:
http://arxiv.org/abs/2407.15845
Autor:
Buzaglo, Gon, Haim, Niv, Yehudai, Gilad, Vardi, Gal, Oz, Yakir, Nikankin, Yaniv, Irani, Michal
Memorization of training data is an active research area, yet our understanding of the inner workings of neural networks is still in its infancy. Recently, Haim et al. (2022) proposed a scheme to reconstruct training samples from multilayer perceptro
Externí odkaz:
http://arxiv.org/abs/2307.01827
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 samples from neural network binary classifiers, based on theoretical re
Externí odkaz:
http://arxiv.org/abs/2305.03350
Diffusion models exhibited tremendous progress in image and video generation, exceeding GANs in quality and diversity. However, they are usually trained on very large datasets and are not naturally adapted to manipulate a given input image or video.
Externí odkaz:
http://arxiv.org/abs/2211.11743
Understanding to what extent neural networks memorize training data is an intriguing question with practical and theoretical implications. In this paper we show that in some cases a significant fraction of the training data can in fact be reconstruct
Externí odkaz:
http://arxiv.org/abs/2206.07758
Autor:
Haim, Niv, Feinstein, Ben, Granot, Niv, Shocher, Assaf, Bagon, Shai, Dekel, Tali, Irani, Michal
GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single video, rendering them almost impractical. In this paper we question the n
Externí odkaz:
http://arxiv.org/abs/2205.05725
Autor:
Haim, Niv, Feinstein, Ben, Granot, Niv, Shocher, Assaf, Bagon, Shai, Dekel, Tali, Irani, Michal
GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single video, rendering them almost impractical. In this paper we question the n
Externí odkaz:
http://arxiv.org/abs/2109.08591
A basic operation in Convolutional Neural Networks (CNNs) is spatial resizing of feature maps. This is done either by strided convolution (donwscaling) or transposed convolution (upscaling). Such operations are limited to a fixed filter moving at pre
Externí odkaz:
http://arxiv.org/abs/2006.11120
Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks. So far, such representations were computed using either: (i) pre-computed implicit shape representations
Externí odkaz:
http://arxiv.org/abs/2002.10099
The level sets of neural networks represent fundamental properties such as decision boundaries of classifiers and are used to model non-linear manifold data such as curves and surfaces. Thus, methods for controlling the neural level sets could find m
Externí odkaz:
http://arxiv.org/abs/1905.11911