AI Chat AI Image Generator AI Video Text to Speech

Reconstructing Network Inputs with Additive Perturbation Signatures

04/11/2019

∙

by Nick Moran, et al.

∙

∙

In this work, we present preliminary results demonstrating the ability to recover a significant amount of information about secret model inputs given only very limited access to model outputs and the ability evaluate the model on additive perturbations to the input.

Nick Moran
7 publications
Chiraag Juvekar
6 publications

research

∙ 04/06/2021

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models

Although end-to-end automatic speech recognition (e2e ASR) models are wi...

0 Zhiyun Lu, et al. ∙

research

∙ 03/25/2021

Additive Tridiagonal Codes over 𝔽_4

In this paper, we introduce a additive Tridiagonal and Double-Tridiagona...

0 N. Annamalai, et al. ∙

research

∙ 01/30/2018

Robustness of classification ability of spiking neural networks

It is well-known that the robustness of artificial neural networks (ANNs...

0 Jie Yang, et al. ∙

research

∙ 11/27/2017

Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation

This paper proposes a new algorithm for controlling classification resul...

0 YoungJoon Yoo, et al. ∙

research

∙ 02/12/2018

Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks

High sensitivity of neural networks against malicious perturbations on i...

0 Yusuke Tsuzuku, et al. ∙

research

∙ 09/05/2019

Additive function approximation in the brain

Many biological learning systems such as the mushroom body, hippocampus,...

0 Kameron Decker Harris, et al. ∙

research

∙ 09/01/2021

Shared Certificates for Neural Network Verification

Existing neural network verifiers compute a proof that each input is han...

0 Christian Sprecher, et al. ∙