FADER: Fast Adversarial Example Rejection
Preprint
Abstract
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from legitimate training samples at different layer representations - a behavior normally exhibited by adversarial attacks. Despite technical differences, all aforementioned methods share a common backbone structure that we formalize and highlight in this contribution, as it can help in identifying promising research directions and drawbacks of existing methods. The first main contribution of this work is the review of these detection methods in the form of a unifying framework designed to accommodate both existing defenses and newer ones to come. In terms of drawbacks, the overmentioned defenses require comparing input samples against an oversized number of reference prototypes, possibly at different representation layers, dramatically worsening the test-time efficiency. Besides, such defenses are typically based on ensembling classifiers with heuristic methods, rather than optimizing the whole architecture in an end-to-end manner to better perform detection. As a second main contribution of this work, we introduce FADER, a novel technique for speeding up detection-based methods. FADER overcome the issues above by employing RBF networks as detectors: by fixing the number of required prototypes, the runtime complexity of adversarial examples detectors can be controlled. Our experiments outline up to 73x prototypes reduction compared to analyzed detectors for MNIST dataset and up to 50x for CIFAR10 dataset respectively, without sacrificing classification accuracy on both clean and adversarial data.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Do gradient-based explanations tell anything about adversarial robustness to android malware?International Journal of Machine Learning and Cybernetics, 2021
- Breast cancer detection by leveraging Machine LearningICT Express, 2020
- The rise of machine learning for detection and classification of malware: Research developments, trends and challengesJournal of Network and Computer Applications, 2020
- Radial Basis Function Network: Its Robustness and Ability to Mitigate Adversarial Examples2019
- Wild patterns: Ten years after the rise of adversarial machine learningPattern Recognition, 2018
- Deep Residual Learning for Image Recognition2016
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Multiple classifier systems for robust classifier design in adversarial environmentsInternational Journal of Machine Learning and Cybernetics, 2010
- Mining adversarial patterns via regularized loss minimizationMachine Learning, 2010
- Learning to classify with missing and corrupted featuresMachine Learning, 2009