A3T: Adversarially Augmented Adversarial Training

2018/01/12 by Akram Erraqabi, Erraqabi, Akram, Aristide Baratin +5 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Bacillus and Francisella bacterial research #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1801.04055

accepted for an oral presentation in Machine Deception Workshop, NIPS 2017

arxiv created 2018/01/12 · arxiv updated 2018/01/15

Abstract

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.

Citations

• Practical Black-Box Attacks against Machine Learning

Cited by

• Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations

Related

• Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
• Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system
• Towards Adversarial Training with Moderate Performance Improvement for Neural Network Classification
• A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies
• A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness