Improving Adversarial Robustness of Ensembles with Diversity Training
Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a surrogate model tends to transfer to the target model. We show that an ensemble of models with misaligned loss gradients can provide an effective defense against transfer-based attacks. Our key insight is that an adversarial example is less likely to fool multiple models in the ensemble if their loss functions do not increase in a correlated fashion. To this end, we propose Diversity Training, a novel method to train an ensemble of models with uncorrelated loss functions. We show that our method significantly improves the adversarial robustness of ensembles and can also be combined with existing methods to create a stronger defense.
Code (1)
Tasks
Adversarial RobustnessDiversitySimilar Papers 제목 키워드 기반
Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Er…
Adversarial RobustnessDiversityExploring Model Learning Heterogeneity for Boosting Ensemble Robustness
Deep neural network ensembles hold the potential of improving generalization performance for complex learning tasks. This paper presents formal analysis and empirical evaluation to show that heterogeneous deep ensembles …
Diversityobject-detectionObject DetectionSemantic SegmentationLOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
Transferability of adversarial examples is a well-known property that endangers all classification models, even those that are only accessible through black-box queries. Prior work has shown that an ensemble of models is…
The Diversity Metrics of Sub-models based on SVD of Jacobians for Ensembles Adversarial Robustness
Transferability of adversarial samples under different CNN models is not only one of the metrics indicators for evaluating the performance of adversarial examples, but also an important research direction in the defense …
Adversarial RobustnessAttributeAttribute ExtractionDimensionality Reduction+1Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness
Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly dist…
DiversityEnsemble Learning