Biased Multi-Domain Adversarial Training
Several recent studies have shown that the use of extra in-distribution data can lead to a high level of adversarial robustness. However, there is no guarantee that it will always be possible to obtain sufficient extra data for a selected dataset. In this paper, we propose a biased multi-domain adversarial training (BiaMAT) method that induces training data amplification using freely available auxiliary datasets. The proposed method can achieve increased adversarial robustness on a primary dataset by leveraging auxiliary datasets via multi-domain learning. Specifically, data amplification on both robust and non-robust features can be accomplished through the application of BiaMAT as demonstrated through an additional analysis based on shuffle testing. Our experimental results indicate that BiaMAT can effectively utilize the robust and non-robust features present in various auxiliary datasets. Moreover, we demonstrate that while existing methods are vulnerable to negative transfer due to the distributional discrepancy between auxiliary and primary data, the proposed method enables neural networks to flexibly leverage diverse image datasets for adversarial training by successfully handling the domain discrepancy through the application of a confidence-based selection strategy.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
BiasAdv: Bias-Adversarial Augmentation for Model Debiasing
Neural networks are often prone to bias toward spurious correlations inherent in a dataset, thus failing to generalize unbiased test criteria. A key challenge to resolving the issue is the significant lack of bias-co…
Adversarial AttackData AugmentationmodelWe Need to Talk About Random Splits
Gorman and Bedrick (2019) argued for using random splits rather than standard splits in NLP experiments. We argue that random splits, like standard splits, lead to overly optimistic performance estimates. We can also spl…
Domain AdaptationRobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient Search
Deep neural networks (DNNs) often face challenges due to their vulnerability to various adversarial perturbations, including false perturbations that undermine prediction accuracy and biased perturbations that cause bias…
Data AugmentationFairnessquantile regressionLearning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain. Ideally, the source and target distributions should be aligned to each o…
Domain AdaptationPseudo LabelTransfer LearningUnbiased Decisions Reduce Regret: Adversarial Domain Adaptation for the Bank Loan Problem
In many real world settings binary classification decisions are made based on limited data in near real-time, e.g. when assessing a loan application. We focus on a class of these problems that share a common feature: the…
Binary ClassificationDomain AdaptationFairness