A3T: Adversarially Augmented Adversarial Training

By Akram Erraqabi, Aristide Baratin, Yoshua Bengio, Simon Lacoste-Julien. 2018

9 citations recorded by the source corpus.

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification models, including deep learning models, are highly vulnerable to adversarial attacks. In this work, we investigate a procedure to improve adversarial robustness of deep neural networks through enforcing representation invariance. The idea is to train the classifier jointly with a discriminator attached to one of its hidden layer and trained to filter the adversarial noise. We perform preliminary experiments to test the viability of the approach and to compare it to other standard adversarial training methods.

Subfields: Artificial Intelligence, Molecular Biology, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Safety, Robustness & Interpretability

Citations in the corpus

Adversarial Example Games (2020, background): “[27] also investigate an adversarial game framework as a means for building robust representations in which an additional discriminator is trained to discriminate adversarial example from natural ones, based on the representation of the current classifier.”
On the Sensitivity of Adversarial Robustness to Input Data Distributions (2018, methodology): “We focus on the adversarial training method, arguably the most popular defense method so far due to its simplicity, effectiveness and scalability (Goodfellow et al., 2014; Huang et al., 2015; Kurakin et al., 2016; Madry et al., 2017; Erraqabi et al., 2018).”