Search Results for author: Shai Rozenberg

Found 4 papers, 1 papers with code

Siamese x-vector reconstruction for domain adapted speaker recognition

no code implementations28 Jul 2020 Shai Rozenberg, Hagai Aronowitz, Ron Hoory

With the rise of voice-activated applications, the need for speaker recognition is rapidly increasing.

Domain Adaptation Speaker Recognition

MadNet: Using a MAD Optimization for Defending Against Adversarial Attacks

no code implementations3 Nov 2019 Shai Rozenberg, Gal Elidan, Ran El-Yaniv

Given a deep neural network (DNN) for a classification problem, an application of MAD optimization results in MadNet, a version of the original network, now equipped with an adversarial defense mechanism.

Adversarial Defense Adversarial Robustness

Improved Detection of Adversarial Attacks via Penetration Distortion Maximization

no code implementations25 Sep 2019 Shai Rozenberg, Gal Elidan, Ran El-Yaniv

This paper is concerned with the defense of deep models against adversarial at- tacks.

Playing SNES in the Retro Learning Environment

1 code implementation7 Nov 2016 Nadav Bhonker, Shai Rozenberg, Itay Hubara

The environment is expandable, allowing for more video games and consoles to be easily added to the environment, while maintaining the same interface as ALE.

Atari Games SNES Games

Cannot find the paper you are looking for? You can Submit a new open access paper.