Automated Robustness with Adversarial Training as a Post-Processing Step

09/06/2021
by   Ambrish Rawat, et al.
0

Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a simple post processing step in yielding robust deep learning model. To achieve this, we adopt adversarial training as a post-processing step for optimised network architectures obtained from a neural architecture search algorithm. Specific policies are adopted for tuning the hyperparameters of the different steps, resulting in a fully automated pipeline for generating adversarially robust deep learning models. We evidence the usefulness of the proposed pipeline with extensive experimentation across 11 image classification and 9 text classification tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/03/2021

AdvRush: Searching for Adversarially Robust Neural Architectures

Deep neural networks continue to awe the world with their remarkable per...
research
07/30/2019

Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures

Deep learning models require the configuration of many layers and parame...
research
07/18/2018

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search

While existing work on neural architecture search (NAS) tunes hyperparam...
research
04/04/2018

Btrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior

Robust localisation and identification of vertebrae is an essential part...
research
03/24/2020

BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models

Neural architecture search (NAS) has shown promising results discovering...
research
02/03/2020

Regularizers for Single-step Adversarial Training

The progress in the last decade has enabled machine learning models to a...
research
11/06/2019

User-Intended Doppler Measurement Type Prediction Combining CNNs With Smart Post-Processing

Spectral Doppler measurements are an important part of the standard echo...

Please sign up or login with your details

Forgot password? Click here to reset