paper-with-me

홈 › Papers

Biased Multi-Domain Adversarial Training

2021-09-29 · Saehyung Lee, Hyungyu Lee, Sanghyuk Chun, Sungroh Yoon

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

2023-01-01 · CVPR 2023 1 · Jongin Lim, Youngdong Kim, Byungjai Kim, Chanho Ahn 외

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 Augmentationmodel

We Need to Talk About Random Splits

2020-05-01 · EACL 2021 2 · Anders Søgaard, Sebastian Ebert, Jasmijn Bastings, Katja Filippova

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 Adaptation

RobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient Search

2023-05-18 · Xuran Li, Peng Wu, Kaixiang Dong, Zhen Zhang 외

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 regression

Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling

2022-06-02 · Jian Hu, Haowen Zhong, Junchi Yan, Shaogang Gong 외

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 Learning

Unbiased Decisions Reduce Regret: Adversarial Domain Adaptation for the Bank Loan Problem

2023-08-15 · Elena Gal, Shaun Singh, Aldo Pacchiano, Ben Walker 외

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