Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise

08/12/2020
by   Alex Serban, et al.
33

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most compelling defense, adversarial training, requires a substantial increase in processing time and it has been shown to overfit on the training data. In this paper, we aim to overcome these limitations by training robust models in low data regimes and transfer adversarial knowledge between different models. We train a meta-optimizer which learns to robustly optimize a model using adversarial examples and is able to transfer the knowledge learned to new models, without the need to generate new adversarial examples. Experimental results show the meta-optimizer is consistent across different architectures and data sets, suggesting it is possible to automatically patch adversarial vulnerabilities.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/26/2021

Deep Repulsive Prototypes for Adversarial Robustness

While many defences against adversarial examples have been proposed, fin...
research
08/07/2020

Optimizing Information Loss Towards Robust Neural Networks

Neural Networks (NNs) are vulnerable to adversarial examples. Such input...
research
06/08/2019

Using learned optimizers to make models robust to input noise

State-of-the art vision models can achieve superhuman performance on ima...
research
10/16/2020

Learning Robust Algorithms for Online Allocation Problems Using Adversarial Training

We address the challenge of finding algorithms for online allocation (i....
research
04/25/2020

Improved Adversarial Training via Learned Optimizer

Adversarial attack has recently become a tremendous threat to deep learn...
research
05/15/2017

Extending Defensive Distillation

Machine learning is vulnerable to adversarial examples: inputs carefully...
research
10/14/2015

Improving Back-Propagation by Adding an Adversarial Gradient

The back-propagation algorithm is widely used for learning in artificial...

Please sign up or login with your details

Forgot password? Click here to reset