509 citations · 546 across the 13 of their papers we have counts for
13 papers
Reconstructing Protected Biometric Templates from Binary Authentication Results
Eliron Rahimi, Margarita Osadchy, Orr Dunkelman
Biometric data is considered to be very private and highly sensitive. As such, many methods for biometric template protection were considered over the years -- from biohashing and…
A practical, fast method for solving sum-of-squares problems for very large polynomials
Daniel Keren, Margarita Osadchy, Roi Poranne
Sum of squares (SOS) optimization is a powerful technique for solving problems where the positivity of a polynomials must be enforced. The common approach to solve an SOS problem i…
Dataset Distillation Meets Provable Subset Selection
Murad Tukan, Alaa Maalouf, Margarita Osadchy
Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields. However, training such models requires huge amounts of data, increasing…
A Unified Approach to Coreset Learning
Alaa Maalouf, Gilad Eini, Ben Mussay +2
Coreset of a given dataset and loss function is usually a small weighed set that approximates this loss for every query from a given set of queries. Coresets have shown to be very…
Fuzzy Commitments Offer Insufficient Protection to Biometric Templates Produced by Deep Learning
Danny Keller, Margarita Osadchy, Orr Dunkelman
In this work, we study the protection that fuzzy commitments offer when they are applied to facial images, processed by the state of the art deep learning facial recognition system…
Data-Independent Structured Pruning of Neural Networks via Coresets
Ben Mussay, Daniel Feldman, Samson Zhou +2
Model compression is crucial for deployment of neural networks on devices with limited computational and memory resources. Many different methods show comparable accuracy of the co…
LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network
Fangliang Bai, Jinchao Liu, Xiaojuan Liu +3
Recent work showed neural-network-based approaches to reconstructing images from compressively sensed measurements offer significant improvements in accuracy and signal compression…
Data-Independent Neural Pruning via Coresets
Ben Mussay, Margarita Osadchy, Vladimir Braverman +2
Previous work showed empirically that large neural networks can be significantly reduced in size while preserving their accuracy. Model compression became a central research topic,…
Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning
Jinchao Liu, Stuart J. Gibson, Margarita Osadchy
Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning…
Dynamic Spectrum Matching with One-shot Learning
Jinchao Liu, Stuart J. Gibson, James Mills +1
Convolutional neural networks (CNN) have been shown to provide a good solution for classification problems that utilize data obtained from vibrational spectroscopy. Moreover, CNNs…
Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution
Jinchao Liu, Margarita Osadchy, Lorna Ashton +3
Machine learning methods have found many applications in Raman spectroscopy, especially for the identification of chemical species. However, almost all of these methods require non…
Latent Hinge-Minimax Risk Minimization for Inference from a Small Number of Training Samples
Dolev Raviv, Margarita Osadchy
Deep Learning (DL) methods show very good performance when trained on large, balanced data sets. However, many practical problems involve imbalanced data sets, or/and classes with…
HoneyFaces: Increasing the Security and Privacy of Authentication Using Synthetic Facial Images
Mor Ohana, Orr Dunkelman, Stuart Gibson +1
One of the main challenges faced by Biometric-based authentication systems is the need to offer secure authentication while maintaining the privacy of the biometric data. Previous…